INDEX

Explanations

information related to statistical comparisons and rankings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ÃŃv

-0.15

/***/

-0.15

izar

-0.14

 Unexpected

-0.14

baugh

-0.14

[section

-0.14

uka

-0.14

iais

-0.14

ando

-0.14

itta

-0.14

POSITIVE LOGITS

abouts

0.15

ave

0.14

Jeg

0.14

 embed

0.14

0.13

crest

0.13

imin

0.13

 egret

0.12

.cd

0.12

_integral

0.12

Activations Density 0.096%

information related to statistical comparisons and rankings

No Comments

No Known Activations

information related to statistical comparisons and rankings

No Comments

No Known Activations