INDEX

Explanations

content related to terms and conditions or legal disclaimers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 ìĥĪê¸Ģ

-0.17

imens

-0.15

.nlm

-0.14

iyim

-0.14

ç¿

-0.13

dez

-0.13

alis

-0.13

tas

-0.13

hod

-0.13

oogle

-0.13

POSITIVE LOGITS

 terms

0.46

 Terms

0.45

Terms

0.40

terms

0.39

/terms

0.38

 privacy

0.38

 Privacy

0.35

 TERMS

0.35

 policies

0.34

_terms

0.33

Activations Density 0.148%

content related to terms and conditions or legal disclaimers

No Comments

No Known Activations