INDEX

Explanations

repeated references to a specific subject or event

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

andom

-0.18

uela

-0.15

-0.14

burg

-0.14

eli

-0.14

 thá»ĭ

-0.13

 Vent

-0.13

ÄĲT

-0.13

è¥

-0.13

 inev

-0.13

POSITIVE LOGITS

uiten

0.15

onn

0.15

mayÄ±

0.15

umont

0.14

åªĴä½ĵ

0.14

à¥ģà¤¹

0.14

.openg

0.14

evin

0.14

Unused

0.14

inton

0.13

Activations Density 0.068%

repeated references to a specific subject or event

No Comments

No Known Activations