INDEX

Explanations

emotional expressions and reactions in characters

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

amen

-0.16

uede

-0.15

itas

-0.15

jed

-0.14

pos

-0.14

æĤ

-0.14

igi

-0.14

pos

-0.14

beck

-0.14

est

-0.13

POSITIVE LOGITS

Ð²ÐµÑī

0.15

oppel

0.15

'field

0.14

Ð¼Ð¾

0.14

ãĥ¼ãĥĭ

0.14

omite

0.14

rowsers

0.14

aille

0.13

 gains

0.13

 Roose

0.13

Activations Density 0.318%

emotional expressions and reactions in characters

No Comments

No Known Activations