INDEX

Explanations

words and phrases associated with measurement or assessment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

abl

-0.18

acz

-0.17

wat

-0.17

dep

-0.17

emat

-0.15

Geh

-0.15

-0.14

 Wikip

-0.14

int

-0.14

POSITIVE LOGITS

raud

0.18

atta

0.17

aternity

0.17

Ã¦re

0.16

iard

0.16

@c

0.15

ilated

0.15

odesk

0.14

jsc

0.14

@brief

0.14

Activations Density 0.019%

words and phrases associated with measurement or assessment

No Comments

No Known Activations