INDEX

Explanations

punctuation marks and formatting variations 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ystore

-0.16

.FILES

-0.15

ipay

-0.14

/>.

-0.14

qli

-0.14

.bundle

-0.14

ÙħÙĪØ¯

-0.14

 Maul

-0.14

ØŃÙĨ

-0.13

.hl

-0.13

POSITIVE LOGITS

auty

0.16

nger

0.15

ãģ®ãģĭ

0.14

WS

0.14

gps

0.14

ainter

0.14

perf

0.13

æľŁ

0.13

 white

0.13

 followed

0.13

Activations Density 0.001%

punctuation marks and formatting variations in the text

No Comments

No Known Activations