INDEX

Explanations

references to proximity or distance to nearby locations or establishments

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

anch

-0.18

hek

-0.16

acock

-0.15

kel

-0.14

urum

-0.14

éģ

-0.14

ulse

-0.13

 Bottom

-0.13

wers

-0.13

 scar

-0.13

POSITIVE LOGITS

/close

0.16

 Bout

0.15

matched

0.14

quier

0.14

laws

0.14

Ø¨ØŃ

0.14

{{{

0.13

/on

0.13

Batch

0.13

Activations Density 0.008%

references to proximity or distance to nearby locations or establishments

No Comments

No Known Activations