INDEX

Explanations

titles and key information related to television series episodes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 gram

-0.17

 Mein

-0.15

igen

-0.15

 Gram

-0.14

Ã¼le

-0.14

clo

-0.14

erald

-0.14

 Greenwood

-0.14

dot

-0.14

mus

-0.14

POSITIVE LOGITS

Å¡ov

0.16

phinx

0.15

(equalTo

0.15

undra

0.15

antes

0.15

alara

0.15

otal

0.14

ioxide

0.14

morgan

0.14

Éµ

0.14

Activations Density 1.277%

titles and key information related to television series episodes

No Comments

No Known Activations