INDEX

Explanations

references to the coronavirus and related terminology

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

iful

-0.18

oku

-0.15

ÃĹ↵↵

-0.15

 OMIT

-0.15

ÑģÑĤÑĢ

-0.14

áº»

-0.14

/libs

-0.14

Ð¾ÑĩÑĮ

-0.14

erson

-0.14

ordinate

-0.14

POSITIVE LOGITS

(es

0.17

plen

0.16

western

0.15

CD

0.14

Äįi

0.14

 willing

0.14

Å¯l

0.14

allo

0.14

 Rena

0.14

Activations Density 0.009%

references to the coronavirus and related terminology

No Comments

No Known Activations