INDEX

Explanations

sequences of words or phrases that are likely to be quoted or referenced

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ivy

-0.15

YPE

-0.14

 DependencyProperty

-0.14

alore

-0.14

ipt

-0.14

 franca

-0.14

orthy

-0.14

uC

-0.13

acie

-0.13

hek

-0.13

POSITIVE LOGITS

(The

0.14

engl

0.14

 bist

0.14

mens

0.14

 Rockefeller

0.14

 chill

0.13

Î»Î¹Î¬

0.13

/The

0.13

uled

0.13

-oper

0.13

Activations Density 0.165%

sequences of words or phrases that are likely to be quoted or referenced

No Comments

No Known Activations