INDEX

Explanations

phrases or terms that indicate new positions or roles within organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

olia

-0.19

ing

-0.17

gag

-0.15

al

-0.15

 stagger

-0.15

al

-0.15

-0.14

ese

-0.14

ru

-0.14

POSITIVE LOGITS

toi

0.16

éĺħè¯»æ¬¡æķ°

0.15

ÄĽÅ¾

0.15

_bug

0.15

imals

0.15

Reject

0.14

çĽĳåĲ¬é¡µéĿ¢

0.14

imir

0.14

.flex

0.14

voy

0.14

Activations Density 0.036%

phrases or terms that indicate new positions or roles within organizations

No Comments

No Known Activations