INDEX

Explanations

references to arms or related actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

.wp

-0.15

egral

-0.15

lfw

-0.15

Sock

-0.15

apis

-0.14

egin

-0.14

ampie

-0.14

æ³

-0.14

osing

-0.14

iating

-0.14

POSITIVE LOGITS

illary

0.17

udu

0.15

chair

0.15

cess

0.15

imax

0.15

Ã¨s

0.14

eced

0.14

Ð±Ñĥ

0.14

rena

0.14

izu

0.14

Activations Density 0.015%

references to arms or related actions

No Comments

No Known Activations