INDEX

Explanations

references to specific instances or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

on

-0.17

egral

-0.15

iÃª

-0.14

ildi

-0.14

èħ

-0.14

å¼ı

-0.14

forcements

-0.13

onaut

-0.13

Ã¤ge

-0.13

cak

-0.13

POSITIVE LOGITS

 behalf

0.51

 occasions

0.39

 occasion

0.39

 basis

0.36

basis

0.32

occasion

0.31

 grounds

0.28

_basis

0.24

 Basis

0.23

 dime

0.21

Activations Density 0.832%

references to specific instances or occurrences

No Comments

No Known Activations