INDEX

Explanations

the presence of the word "ent."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iface

-0.17

bjerg

-0.17

obili

-0.17

zell

-0.16

esch

-0.15

Ã©ro

-0.15

.js

-0.15

otime

-0.15

stown

-0.14

eer

-0.14

POSITIVE LOGITS

stin

0.17

ius

0.16

setError

0.14

LOWER

0.14

NOP

0.14

ãĥ¼ãĤ¸

0.14

amarin

0.14

EPS

0.14

anela

0.14

den

0.14

Activations Density 0.000%

the presence of the word "ent."

No Comments

No Known Activations