INDEX

Explanations

numerical data and statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ERG

-0.15

illisecond

-0.15

enny

-0.14

fuse

-0.14

Bom

-0.14

rani

-0.14

odnÃŃ

-0.14

assen

-0.14

iden

-0.13

vit

-0.13

POSITIVE LOGITS

none

0.16

 none

0.15

0.14

acs

0.14

 unreachable

0.14

eting

0.14

.Gr

0.14

 nÃło

0.13

 McInt

0.13

 neither

0.13

Activations Density 0.005%

numerical data and statistical information

No Comments

No Known Activations