INDEX

Explanations

affirmative statements or approvals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

brero

-0.15

rosse

-0.15

umont

-0.15

regor

-0.15

 Continue

-0.14

ockey

-0.14

occo

-0.14

aine

-0.14

roit

-0.14

oods

-0.14

POSITIVE LOGITS

 Marks

0.19

 bites

0.17

Marks

0.17

ãĥĬãĥ¼

0.16

Hack

0.15

 tiener

0.15

 ÑĤÑĢÑĥÐ±

0.15

baz

0.15

ONGLONG

0.15

Naj

0.14

Activations Density 0.000%

affirmative statements or approvals

No Comments

No Known Activations