INDEX

Explanations

references to exclusive or limited access groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

asca

-0.15

ãĥ¼ãĥĢ

-0.15

avin

-0.14

imd

-0.14

à¤Ĺà¤²

-0.13

oras

-0.13

illes

-0.13

ÏĨÎ±

-0.13

zer

-0.13

lÃ¡n

-0.13

POSITIVE LOGITS

few

0.65

 handful

0.62

 select

0.58

few

0.57

Few

0.54

Few

0.49

 fewer

0.46

select

0.42

 minority

0.40

 quelques

0.38

Activations Density 0.204%

references to exclusive or limited access groups

No Comments

No Known Activations