INDEX

Explanations

expressions of approval, disapproval, and commendation in the context of organizational or societal matters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

efe

-0.17

³

-0.17

 Spinner

-0.15

ean

-0.15

IRROR

-0.14

.relu

-0.14

lez

-0.14

á»«

-0.14

ulan

-0.14

ead

-0.14

POSITIVE LOGITS

/owl

0.16

Ø·Ùģ

0.15

istrovstvÃŃ

0.14

pha

0.14

Î´Î¬

0.14

 åĮ

0.14

 íĬ¹íŀĪ

0.14

 Michaels

0.14

bip

0.13

_PF

0.13

Activations Density 0.169%

expressions of approval, disapproval, and commendation in the context of organizational or societal matters

No Comments

No Known Activations