INDEX

Explanations

patterns of comparison and contrasts in statements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

urma

-0.15

-0.14

 LÃ¢m

-0.14

chet

-0.14

kinson

-0.14

owa

-0.14

 Threshold

-0.14

urf

-0.14

à¸ļà¸ļ

-0.14

 anywhere

-0.14

POSITIVE LOGITS

uant

0.17

Salir

0.16

erin

0.16

erie

0.14

ged

0.14

dc

0.13

unci

0.13

bad

0.13

ania

0.13

 Estr

0.13

Activations Density 0.115%

patterns of comparison and contrasts in statements

No Comments

No Known Activations