INDEX

Explanations

instances of the word "on" in varying contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

raits

-0.15

fÃ¼g

-0.15

¼åĲĪ

-0.15

omid

-0.15

enaire

-0.15

ButtonModule

-0.14

curacy

-0.14

ebo

-0.14

oms

-0.14

unas

-0.14

POSITIVE LOGITS

ep

0.15

thew

0.14

richt

0.14

unker

0.14

yl

0.14

oÄŁ

0.14

ï¸

0.14

atre

0.13

ait

0.13

ens

0.13

Activations Density 0.030%

instances of the word "on" in varying contexts

No Comments

No Known Activations