INDEX

Explanations

references to movies and related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

avin

-0.17

ioni

-0.16

forth

-0.16

egie

-0.15

rodu

-0.15

lant

-0.14

 CreateMap

-0.14

uba

-0.14

cona

-0.14

 Grill

-0.14

POSITIVE LOGITS

AccessType

0.17

astes

0.14

ayar

0.14

omain

0.14

arial

0.13

.toolbox

0.13

}}],↵

0.13

/browser

0.13

umbo

0.13

 Bullet

0.13

Activations Density 0.025%

references to movies and related content

No Comments

No Known Activations