INDEX

Explanations

instances of the word "it" and similar pronouns relating to subjects or objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

agu

-0.16

heimer

-0.16

ÑıÐ¶

-0.16

.localization

-0.15

ayette

-0.15

EObject

-0.15

arih

-0.15

edral

-0.14

alez

-0.14

POSITIVE LOGITS

 stands

0.19

 stand

0.19

stands

0.17

standing

0.17

stand

0.16

 Stand

0.16

 stood

0.15

rape

0.15

 standing

0.15

andle

0.15

Activations Density 0.009%

instances of the word "it" and similar pronouns relating to subjects or objects

No Comments

No Known Activations