INDEX

Explanations

instances of classification categories, particularly "Uncategorized."

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

ocz

-0.18

ahun

-0.15

ubes

-0.14

&a

-0.13

andles

-0.13

finger

-0.13

iali

-0.13

Ãºng

-0.13

erville

-0.13

ERCHANT

-0.13

POSITIVE LOGITS

 enact

0.14

ellaneous

0.14

fug

0.14

ments

0.14

ird

0.14

 proven

0.14

ãĥ

0.14

imentary

0.14

WC

0.14

gram

0.14

Activations Density 0.004%

instances of classification categories, particularly "Uncategorized."

No Comments

No Known Activations