INDEX

Explanations

words related to geographical locations or specific places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

Ìī

-0.15

reh

-0.15

Uns

-0.15

ë°Ģ

-0.15

 brows

-0.14

 pymysql

-0.14

FillColor

-0.14

ÑĥÑĢÐ³

-0.14

kers

-0.13

åŃĹ

-0.13

POSITIVE LOGITS

quit

0.16

 sorts

0.15

awning

0.15

.TabStop

0.15

Quit

0.14

ĨĴ

0.14

Sort

0.14

 quit

0.14

ī´

0.13

èķī

0.13

Activations Density 0.105%

words related to geographical locations or specific places

No Comments

No Known Activations