INDEX

Explanations

references to publications and special issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

oplan

-0.15

ÑĢÐµÐ´

-0.15

assen

-0.15

atement

-0.15

ÏĥÏĩ

-0.14

achsen

-0.14

imits

-0.14

enso

-0.14

insk

-0.14

enerator

-0.14

POSITIVE LOGITS

 Alley

0.18

Ìĥ

0.17

ondo

0.16

Sez

0.15

egg

0.15

erer

0.15

lings

0.14

nh

0.14

pedia

0.14

 Pond

0.14

Activations Density 0.216%

references to publications and special issues

No Comments

No Known Activations