INDEX

Explanations

references to the origin of information or resources

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

alu

-0.16

alles

-0.16

infeld

-0.15

ë¡Ŀ

-0.15

æķ·

-0.14

avigate

-0.14

;element

-0.14

ÑĨÐµÐ¿

-0.14

ÙĨØ¯Ø±

-0.13

elda

-0.13

POSITIVE LOGITS

 sources

1.07

 source

0.94

sources

0.85

 Sources

0.85

source

0.78

Sources

0.74

 Source

0.74

-source

0.71

Source

0.70

 Ð¸ÑģÑĤÐ¾Ñĩ

0.69

Activations Density 0.196%

references to the origin of information or resources

No Comments

No Known Activations