INDEX

Explanations

instances of corrections and clarifications in statements

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

inks

-0.17

igner

-0.16

orum

-0.15

wick

-0.15

asts

-0.15

ugh

-0.14

insky

-0.14

 Collaboration

-0.14

Ø§Ø±Øª

-0.14

ipher

-0.14

POSITIVE LOGITS

cz

0.16

 Demon

0.14

cta

0.14

(DialogInterface

0.14

ennen

0.14

ikon

0.13

Ã¡Äį

0.13

 Halk

0.13

 Demo

0.13

 Resolution

0.13

Activations Density 0.286%

instances of corrections and clarifications in statements

No Comments

No Known Activations