INDEX

Explanations

references to stamps and commemorative items

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

llum

-0.15

ê´ĳ

-0.14

 odpad

-0.13

uka

-0.13

ubb

-0.13

ngÃ¶r

-0.13

 Ð¾ÑĤÐ²ÐµÑĢ

-0.13

astes

-0.13

Âłmi

-0.13

aud

-0.12

POSITIVE LOGITS

 showing

0.59

 show

0.56

 shows

0.56

 showed

0.54

show

0.52

-show

0.50

 Showing

0.48

shows

0.47

_show

0.44

Showing

0.44

Activations Density 0.219%

references to stamps and commemorative items

No Comments

No Known Activations