INDEX

Explanations

references to abstract concepts or general terms suggesting multiple options or variations

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

oux

-0.16

aight

-0.16

Ã¢r

-0.16

-0.15

 Pazar

-0.15

æĤ

-0.15

uur

-0.15

/assert

-0.15

-0.14

ÃŃr

-0.14

POSITIVE LOGITS

ugu

0.15

ÑĸÐ½ÑĮ

0.15

 Schneider

0.15

Vul

0.14

nbsp

0.14

dÃ¼r

0.14

 ì§

0.13

ÏĢÎµÎ¹

0.13

ì±ħ

0.13

iem

0.13

Activations Density 0.257%

references to abstract concepts or general terms suggesting multiple options or variations

No Comments

No Known Activations