INDEX

Explanations

programming structure comments and related metadata

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Singer

-0.16

ega

-0.15

ocal

-0.14

gÄ±

-0.14

attery

-0.14

enci

-0.13

eree

-0.13

âĶĶ

-0.13

ather

-0.13

 Nath

-0.13

POSITIVE LOGITS

param

0.35

 param

0.34

@param

0.30

åıĤæķ°

0.29

 argument

0.29

-param

0.29

 Parameters

0.29

 parameter

0.28

 arguments

0.28

 parameters

0.27

Activations Density 0.030%

programming structure comments and related metadata

No Comments

No Known Activations