INDEX

Explanations

references to the pronoun "you."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

eer

-0.19

agas

-0.16

ï»¿↵↵

-0.16

aler

-0.15

 Awareness

-0.15

gnore

-0.15

Ø¨Ø§ÙĨ

-0.14

Ð¾Ð¸ÑĤ

-0.14

ango

-0.14

 Knowledge

-0.14

POSITIVE LOGITS

 know

0.37

know

0.29

 Know

0.25

Know

0.24

 knows

0.20

KN

0.18

çŁ¥éģĵ

0.17

 KNOW

0.16

çŁ¥

0.16

 mentioned

0.15

Activations Density 0.028%

references to the pronoun "you."

No Comments

No Known Activations