INDEX

Explanations

numerical or date-related information in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ÑĢÑĥÐ½

-0.17

åıĸãĤĬ

-0.15

actionDate

-0.15

-ts

-0.15

oped

-0.15

unist

-0.14

à¸Ļà¸²à¸Ļ

-0.14

zano

-0.14

toa

-0.13

_sequences

-0.13

POSITIVE LOGITS

 Furn

0.17

mil

0.16

rr

0.15

avanaugh

0.15

anych

0.14

 smack

0.14

ario

0.14

 getchar

0.14

ry

0.13

mil

0.13

Activations Density 0.018%

numerical or date-related information in the text

No Comments

No Known Activations