INDEX

Explanations

references to historical figures or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Äįky

-0.16

 Newtown

-0.16

urtle

-0.15

è¯ī

-0.15

 ZÃ¡kladnÃŃ

-0.14

ÑĢÐ¾Ñĩ

-0.14

 eldre

-0.14

 Fayette

-0.14

 Satoshi

-0.13

izzard

-0.13

POSITIVE LOGITS

 Nielsen

0.36

 Andersen

0.36

Bj

0.36

 Lund

0.36

gaard

0.35

 Jensen

0.34

holm

0.34

 Hansen

0.34

 Svens

0.34

 Lars

0.33

Activations Density 0.113%

references to historical figures or events

No Comments

No Known Activations