INDEX

Explanations

punctuation marks and their associated contexts in text

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

BERS

-0.16

ppe

-0.16

ç¦

-0.16

ispers

-0.16

eyn

-0.16

warts

-0.15

åĬ¨çĶŁæĪĲ

-0.15

bers

-0.15

perienced

-0.14

Î½Ïİ

-0.14

POSITIVE LOGITS

 pressed

0.17

 Rank

0.16

sf

0.15

Ort

0.15

åĿĤ

0.15

à¹Īà¸Ńà¸¡

0.15

orts

0.14

 crack

0.14

tle

0.14

umb

0.14

Activations Density 0.001%

punctuation marks and their associated contexts in text

No Comments

No Known Activations