INDEX

Explanations

copyright and ownership-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Ìģt

-0.15

oub

-0.15

-0.14

Ìģ

-0.14

Ã²i

-0.14

 Fountain

-0.14

ateur

-0.14

ÌĢ

-0.14

kus

-0.14

lea

-0.14

POSITIVE LOGITS

ahat

0.17

 dikke

0.16

erli

0.15

AdapterFactory

0.15

lopen

0.15

epend

0.15

copyright

0.15

ken

0.15

oya

0.15

ãĤ¥

0.14

Activations Density 0.397%

copyright and ownership-related terms

No Comments

No Known Activations