INDEX

Explanations

instances of deleted content or information that has been removed

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

ÙĦØ§Øª

-0.15

.Shapes

-0.14

FRINGEMENT

-0.14

particle

-0.14

.directive

-0.14

ammen

-0.14

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

-0.14

Particle

-0.13

 conver

-0.13

Ost

-0.13

POSITIVE LOGITS

afil

0.16

uck

0.16

viar

0.15

-archive

0.14

sid

0.14

ãĤĵãģ©

0.14

 Mellon

0.14

Sid

0.14

obao

0.14

Zum

0.13

Activations Density 0.001%

instances of deleted content or information that has been removed

No Comments

No Known Activations