INDEX

Explanations

specific numeric values and terms relevant to measurements or assessments

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

-0.17

......

-0.16

...'

-0.16

...↵↵

-0.15

Www

-0.15

......↵↵

-0.15

ucher

-0.14

 "...

-0.14

 âĢĲ

-0.14

 ÐĿÐ°Ð³

-0.13

POSITIVE LOGITS

 fucking

0.20

 bullshit

0.18

 shitty

0.18

 fucked

0.17

 fuck

0.17

 fucks

0.16

 asshole

0.16

 Fucking

0.16

 shit

0.15

 bitch

0.15

Activations Density 0.001%

specific numeric values and terms relevant to measurements or assessments

No Comments

No Known Activations