INDEX

Explanations

mentions of specific locations or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

/the

-0.15

ãĥŃãĥ³

-0.14

let

-0.14

_SRC

-0.13

çļĦä¸Ģä¸ª

-0.13

çļĦ

-0.13

ACS

-0.13

InThe

-0.13

orthy

-0.12

innen

-0.12

POSITIVE LOGITS

 same

0.28

same

0.20

.same

0.19

 SAME

0.18

own

0.17

Same

0.17

 Same

0.16

panse

0.15

cÃ©

0.15

EIF

0.14

Activations Density 0.813%

mentions of specific locations or situations

No Comments

No Known Activations