INDEX

Explanations

greetings and introductions in conversations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Threads

-0.15

uckles

-0.15

 correct

-0.15

 Cheers

-0.14

↵

-0.14

ramer

-0.14

avana

-0.14

ucha

-0.14

ingly

-0.14

rial

-0.14

POSITIVE LOGITS

conto

0.18

uen

0.17

ãģĵãĤĵãģ«ãģ¡ãģ¯

0.17

olen

0.16

æ¬¢

0.16

ãģĵãĤĵãģ«

0.15

 hello

0.15

istrovstvÃŃ

0.15

ÅĻez

0.15

GRESS

0.15

Activations Density 0.037%

greetings and introductions in conversations

No Comments

No Known Activations