INDEX

Explanations

instances of the word "it" 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

orman

-0.16

rou

-0.16

ded

-0.15

rÃ¡

-0.14

vably

-0.14

pository

-0.14

duino

-0.13

onaut

-0.13

Ð¼Ðµ

-0.13

 rozs

-0.13

POSITIVE LOGITS

 certainly

0.22

 Ð²ÐµÐ´ÑĮ

0.16

0.15

asha

0.15

 Certainly

0.15

elow

0.14

arsi

0.14

amar

0.14

 prive

0.14

Activations Density 0.151%

instances of the word "it" in various contexts

No Comments

No Known Activations