INDEX

Explanations

the word "As" to highlight the start of statements or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 evidenced

-0.15

 bulk

-0.15

anner

-0.15

ayne

-0.14

pany

-0.13

itin

-0.13

ÑĻ

-0.13

RP

-0.13

 Dense

-0.13

POSITIVE LOGITS

ereotype

0.17

 Boeh

0.15

BufferData

0.15

dato

0.14

ocz

0.14

ÏĦÎ¿Î»

0.14

idth

0.14

ë£Į

0.14

inch

0.14

ATO

0.13

Activations Density 0.062%

the word "As" to highlight the start of statements or observations

No Comments

No Known Activations