INDEX

Explanations

numerical data or statistics related to a subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ÏĢÎ¿Ïį

-0.16

feit

-0.15

reib

-0.15

okus

-0.15

uli

-0.15

asjon

-0.14

ync

-0.14

osaur

-0.14

fern

-0.14

ument

-0.14

POSITIVE LOGITS

adm

0.15

ubb

0.15

 iron

0.14

Wor

0.14

 Throw

0.14

//{{

0.14

RAF

0.14

at

0.14

abb

0.14

 grav

0.13

Activations Density 0.009%

numerical data or statistics related to a subject

No Comments

No Known Activations