INDEX

Explanations

repeated instances of the pronoun "I" and its variations, indicating a focus on personal expressions and feelings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

lez

-0.16

zew

-0.16

urgeon

-0.16

 swore

-0.16

.scalablytyped

-0.15

 swear

-0.15

 McCorm

-0.14

iros

-0.14

ocz

-0.14

ãģ¹ãģį

-0.14

POSITIVE LOGITS

Ëĺ

0.17

 Heard

0.15

 told

0.15

Å¡ak

0.15

orde

0.15

otal

0.14

 ÑģÐ¾ÑģÑĤÐ¾Ñı

0.14

etch

0.14

SOR

0.14

etus

0.14

Activations Density 0.208%

repeated instances of the pronoun "I" and its variations, indicating a focus on personal expressions and feelings

No Comments

No Known Activations