INDEX

Explanations

expressions related to personal identity and social roles

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

anela

-0.15

ander

-0.15

 konkrÃ©t

-0.14

 stuff

-0.14

ixo

-0.14

EXPR

-0.14

ods

-0.13

lope

-0.13

 Blonde

-0.13

vt

-0.13

POSITIVE LOGITS

who

0.35

who

0.26

 whose

0.25

Who

0.21

 whom

0.20

 with

0.20

 capable

0.20

 extra

0.20

 unto

0.19

whose

0.19

Activations Density 0.293%

expressions related to personal identity and social roles

No Comments

No Known Activations