INDEX

Explanations

references to historical events or notable individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÐµÑĢÐ³

-0.14

å°ĩ

-0.13

eenth

-0.13

 Gregg

-0.13

rchive

-0.13

utut

-0.13

¢åįķ

-0.13

leich

-0.13

iek

-0.13

Ã©nÃ©

-0.13

POSITIVE LOGITS

0.33

0.32

0.31

0.30

0.29

Activations Density 0.082%

references to historical events or notable individuals

No Comments

No Known Activations