INDEX

Explanations

references to software libraries and their versions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

rams

-0.16

rupa

-0.15

 sleeves

-0.15

kate

-0.15

rame

-0.15

 Mast

-0.14

 kÃ¶ln

-0.14

cko

-0.14

mee

-0.14

/gen

-0.14

POSITIVE LOGITS

 Darling

0.16

quete

0.15

utton

0.14

alam

0.14

quina

0.13

 Bourbon

0.13

Ø¨ÙĬØ±

0.13

iron

0.13

UND

0.13

Activations Density 0.009%

references to software libraries and their versions

No Comments

No Known Activations