INDEX

Explanations

symbols or special characters that may indicate a specific context or formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

('

-0.18

("

-0.15

 Abed

-0.15

á»Ĩ

-0.15

âĢ¦↵↵↵

-0.15

tvrt

-0.15

-0.14

 abdom

-0.14

crate

-0.14

POSITIVE LOGITS

Am

0.19

 casinos

0.19

 Poker

0.19

 casino

0.19

 Casinos

0.18

 poker

0.18

 Casino

0.17

 sites

0.17

 gaming

0.16

 Gambling

0.16

Activations Density 0.002%

symbols or special characters that may indicate a specific context or formatting

No Comments

No Known Activations