INDEX

Explanations

instances of the word "been."

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

éĥİ

-0.17

xes

-0.16

ÌĪ

-0.15

IENTATION

-0.15

ombo

-0.15

yar

-0.14

onec

-0.14

weed

-0.14

yat

-0.14

 VÅ¡ech

-0.14

POSITIVE LOGITS

 lately

0.16

_since

0.15

/is

0.15

zos

0.15

ko

0.15

reek

0.14

 since

0.14

cher

0.13

Activations Density 0.126%

instances of the word "been."

No Comments

No Known Activations

instances of the word "been."

No Comments

No Known Activations