INDEX

Explanations

phrases related to getting lost or confusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

gart

-0.16

 eiusmod

-0.16

á»Ľm

-0.15

 VerfÃ¼gung

-0.15

ziej

-0.15

Ð²ÑĸÐ»ÑĮ

-0.14

bir

-0.14

ilian

-0.14

 hÃ¢l

-0.14

 Nurs

-0.14

POSITIVE LOGITS

 shuffle

0.17

lost

0.17

uet

0.17

 Lost

0.16

 Blanch

0.16

 lost

0.16

 Transition

0.16

 transition

0.15

 translation

0.15

dep

0.15

Activations Density 0.131%

phrases related to getting lost or confusion

No Comments

No Known Activations