INDEX

Explanations

occurrences of the letter 'O' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ptions

-0.18

-0.16

ffer

-0.16

bilt

-0.16

 marg

-0.15

hw

-0.15

bj

-0.15

ver

-0.15

inkle

-0.15

ops

-0.15

POSITIVE LOGITS

uess

0.20

uest

0.18

ise

0.17

cÃ©

0.16

este

0.16

ÑĢÐ°Ð²Ð°

0.16

isans

0.16

sterreich

0.16

tok

0.16

lim

0.16

Activations Density 0.023%

occurrences of the letter 'O' in various contexts

No Comments

No Known Activations