INDEX

Explanations

multi-line comments or documentation blocks in code fragments

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

ÐµÐºÐ¾Ð¼

-0.18

enis

-0.17

enes

-0.16

aston

-0.16

eries

-0.14

bÃŃr

-0.14

Ä°Y

-0.14

 fatt

-0.14

usra

-0.14

agon

-0.13

POSITIVE LOGITS

ê·ł

0.17

ifi

0.15

_bases

0.14

hsi

0.13

 Libert

0.13

emat

0.13

gth

0.13

ķĮ

0.13

RD

0.13

UME

0.13

Activations Density 0.008%

multi-line comments or documentation blocks in code fragments

No Comments

No Known Activations