INDEX

Explanations

references to the character Nancy Drew

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

izr

-0.17

 Zucker

-0.15

egan

-0.14

ulumi

-0.14

aal

-0.14

hv

-0.14

 Freak

-0.14

pty

-0.14

inati

-0.14

omer

-0.14

POSITIVE LOGITS

ä¸»äºº

0.17

 character

0.15

 caracter

0.15

 adventures

0.14

 Character

0.14

 univers

0.14

à¸°

0.14

 PropertyInfo

0.14

characters

0.14

character

0.13

Activations Density 0.128%

references to the character Nancy Drew

No Comments

No Known Activations