INDEX

Explanations

terms related to biographies or historical accounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ridor

-0.15

accumulator

-0.15

ief

-0.13

pecified

-0.13

iline

-0.13

ycin

-0.13

aÄį

-0.13

acker

-0.13

_fk

-0.13

inton

-0.13

POSITIVE LOGITS

ariat

0.17

igate

0.16

 anzeigen

0.15

esan

0.14

iyel

0.13

zza

0.13

 Freder

0.13

 Uncomment

0.13

 æ®

0.13

 Sammy

0.13

Activations Density 0.013%

terms related to biographies or historical accounts

No Comments

No Known Activations