INDEX

Explanations

instances of the word "adjust" and its derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

PEAR

-0.17

ÃĹ↵↵

-0.15

ucas

-0.15

ander

-0.15

ByUsername

-0.15

anÃ¡

-0.15

uento

-0.14

stead

-0.14

anner

-0.14

ropa

-0.14

POSITIVE LOGITS

ments

0.17

sembl

0.15

Hra

0.15

 Corm

0.15

ors

0.15

ìĤ¬íķŃ

0.14

ements

0.14

ably

0.14

ment

0.14

Activations Density 0.036%

instances of the word "adjust" and its derivatives

No Comments

No Known Activations