INDEX

Explanations

web-related actions and functionalities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.17

-0.16

alg

-0.16

ant

-0.15

 radi

-0.15

-0.14

 probation

-0.14

 inst

-0.14

POSITIVE LOGITS

illion

0.16

 Cosby

0.15

cstdint

0.15

CRE

0.15

Slf

0.15

ëıĦë¡ľ

0.14

ãĤıãģĽ

0.14

 Bilg

0.14

ë°Ģ

0.14

 millenn

0.14

Activations Density 0.009%

web-related actions and functionalities

No Comments

No Known Activations