INDEX

Explanations

intensifiers and strong expressions of frustration or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

æ®¿

-0.16

ä¿

-0.15

Ã¡ÅĻ

-0.15

elib

-0.15

ird

-0.15

olland

-0.14

ult

-0.14

ilig

-0.14

 similarly

-0.13

 equally

-0.13

POSITIVE LOGITS

auer

0.17

STE

0.14

 @{↵

0.14

mal

0.14

reation

0.14

Ã©o

0.13

mal

0.13

Mal

0.13

\e

0.13

ØŃÙħ

0.13

Activations Density 0.024%

intensifiers and strong expressions of frustration or emphasis

No Comments

No Known Activations