INDEX

Explanations

variation in the use of personal pronouns and common verbs

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

undy

-0.15

raya

-0.14

à¸ŀà¸£à¸°à¸£à¸²à¸Ĭ

-0.13

 Î§Î±

-0.13

imet

-0.13

bane

-0.13

rome

-0.13

ube

-0.13

@qq

-0.13

POSITIVE LOGITS

 experience

0.15

kea

0.14

 affected

0.14

esel

0.14

Lang

0.14

uppy

0.14

Î¼Î¿

0.14

 Lang

0.14

claim

0.14

Activations Density 0.006%

variation in the use of personal pronouns and common verbs

No Comments

No Known Activations