INDEX

Explanations

references to web-related topics or platforms

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

exion

-0.18

avad

-0.16

fty

-0.16

/load

-0.15

 reverse

-0.15

epad

-0.15

ansson

-0.15

eus

-0.15

Nem

-0.15

ÌĨ

-0.15

POSITIVE LOGITS

isode

0.20

iste

0.19

Sharper

0.17

rier

0.16

dna

0.15

 UClass

0.15

 spun

0.14

tiny

0.14

rought

0.14

Î¹Î½Îµ

0.14

Activations Density 0.024%

references to web-related topics or platforms

No Comments

No Known Activations