INDEX

Explanations

references to governance and political structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

sky

-0.15

dden

-0.14

irk

-0.14

tm

-0.14

wyn

-0.13

 mischief

-0.13

jac

-0.13

 coff

-0.13

 sowie

-0.13

 mycket

-0.13

POSITIVE LOGITS

van

0.18

om

0.18

wa

0.17

 mÃ©t

0.16

qua

0.16

wat

0.16

als

0.16

ssp

0.16

die

0.15

 door

0.15

Activations Density 0.057%

references to governance and political structures

No Comments

No Known Activations

references to governance and political structures

No Comments

No Known Activations