INDEX

Explanations

instances of the letter 'G'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ikki

-0.15

etik

-0.14

 subs

-0.14

ÎºÎ¿ÏĤ

-0.14

.lv

-0.14

åĳĨ

-0.14

-Za

-0.13

etta

-0.13

abe

-0.13

icio

-0.13

POSITIVE LOGITS

arden

0.22

aller

0.22

alleries

0.22

rot

0.21

ilded

0.21

ables

0.20

ypsum

0.20

aler

0.20

0.19

anges

0.19

Activations Density 0.045%

instances of the letter 'G'

No Comments

No Known Activations