INDEX

Explanations

mentions of authors, contributors, or prominent names associated with content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 fuller

-0.15

 otherwise

-0.14

CF

-0.14

OrElse

-0.14

Chron

-0.14

tone

-0.14

setDisplay

-0.14

set

-0.14

 poly

-0.13

 Fuller

-0.13

POSITIVE LOGITS

ampo

0.19

AZY

0.15

esimal

0.15

enis

0.15

krv

0.15

âĻª

0.15

olo

0.14

iminal

0.14

ETO

0.14

oload

0.14

Activations Density 0.007%

mentions of authors, contributors, or prominent names associated with content

No Comments

No Known Activations