INDEX

Explanations

specific terms associated with the media and entertainment industry

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ANCELED

-0.14

unei

-0.14

xes

-0.14

upe

-0.14

ritt

-0.14

Ð»ÑĥÐ³

-0.14

.getvalue

-0.14

nesia

-0.14

ouver

-0.13

/values

-0.13

POSITIVE LOGITS

ICA

0.15

cus

0.14

aves

0.14

inati

0.13

 Rosen

0.13

onn

0.13

ira

0.13

asy

0.13

spa

0.12

Ã©v

0.12

Activations Density 0.579%

specific terms associated with the media and entertainment industry

No Comments

No Known Activations