INDEX

Explanations

references to original creative works and content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 laps

-0.15

 comp

-0.15

-0.14

ono

-0.14

ben

-0.14

ric

-0.14

 manner

-0.14

Hao

-0.14

urs

-0.14

old

-0.13

POSITIVE LOGITS

endoza

0.17

æľį

0.15

atoi

0.15

ampp

0.15

ä»

0.14

èİ

0.14

ulse

0.14

airs

0.13

affle

0.13

orer

0.13

Activations Density 0.213%

references to original creative works and content

No Comments

No Known Activations