INDEX

Explanations

numbers or numerical data associated with classification or categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

lder

-0.14

 tent

-0.14

iterr

-0.14

wf

-0.14

SET

-0.14

eed

-0.14

 wing

-0.14

bv

-0.14

ovich

-0.14

lass

-0.14

POSITIVE LOGITS

ÑĢÐ°ÑħÐ¾Ð²

0.17

aturas

0.17

herits

0.16

 Nass

0.16

aucoup

0.15

ulk

0.15

ahren

0.15

 åĥ

0.15

#__

0.14

odyn

0.14

Activations Density 0.009%

numbers or numerical data associated with classification or categorization

No Comments

No Known Activations