INDEX

Explanations

words related to disassociation or rejection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ays

-0.16

-0.15

quip

-0.15

dez

-0.15

oleÄį

-0.15

fty

-0.14

ë¹Ī

-0.14

Mapped

-0.14

à¸İ

-0.14

hole

-0.14

POSITIVE LOGITS

 miss

0.26

band

0.25

miss

0.23

 Miss

0.22

qual

0.21

bands

0.21

 band

0.21

 misses

0.19

Miss

0.19

 missed

0.19

Activations Density 0.015%

words related to disassociation or rejection

No Comments

No Known Activations