INDEX

Explanations

instances of the word "at" used 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

dorf

-0.17

oret

-0.16

Ã¼z

-0.15

AtIndex

-0.15

at

-0.14

_at

-0.14

ElementException

-0.14

ragen

-0.14

uge

-0.14

bery

-0.14

POSITIVE LOGITS

 least

0.43

/by

0.30

lassian

0.25

least

0.24

rophy

0.23

 times

0.23

Least

0.23

-risk

0.22

-home

0.22

/on

0.22

Activations Density 0.342%

instances of the word "at" used in various contexts

No Comments

No Known Activations