INDEX

Explanations

media-related terminology and project descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

å±±å¸Ĥ

-0.16

 moduleName

-0.15

 Watson

-0.15

//{{

-0.15

opard

-0.15

Wat

-0.15

 moduleId

-0.15

.Module

-0.15

 modules

-0.14

legate

-0.14

POSITIVE LOGITS

Hom

0.26

Hom

0.23

 homogeneous

0.19

hom

0.19

 Hugh

0.19

hom

0.19

Mae

0.18

 Antony

0.18

.fn

0.18

inka

0.17

Activations Density 0.002%

media-related terminology and project descriptions

No Comments

No Known Activations