INDEX

Explanations

names of movies or references to film-related content

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

 rumpe

-0.17

 erotiske

-0.17

 geschichten

-0.16

 frÃ¦kke

-0.16

 prostituerade

-0.15

agem

-0.15

led

-0.15

 bryster

-0.15

Ã¤m

-0.14

á»©

-0.14

POSITIVE LOGITS

sz

0.25

egy

0.24

 rend

0.22

Sz

0.22

gy

0.21

 legs

0.21

 harm

0.21

 pontos

0.19

rend

0.19

 Ã©s

0.19

Activations Density 0.009%

names of movies or references to film-related content

No Comments

No Known Activations