INDEX

Explanations

instances of the word "you" and variations of it in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

odos

-0.17

iban

-0.17

ÙĪÙĦ

-0.14

 cá»Ń

-0.14

amel

-0.14

 factor

-0.14

ãģĬãĤĬ

-0.13

ãĥ³ãĥĲ

-0.13

ynec

-0.13

_RG

-0.13

POSITIVE LOGITS

may

0.22

can

0.20

'll

0.18

 will

0.18

’ll

0.17

ingham

0.17

0.16

cano

0.15

 should

0.14

 must

0.14

Activations Density 0.081%

instances of the word "you" and variations of it in different contexts

No Comments

No Known Activations