INDEX

Explanations

references to time, specifically weeks and days

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ha

-0.15

 Thom

-0.15

/plain

-0.15

 Bren

-0.15

Syn

-0.14

kel

-0.14

á»Ŀ

-0.14

syn

-0.14

ibel

-0.14

/apt

-0.14

POSITIVE LOGITS

Lun

0.17

eyin

0.15

ilig

0.15

 bullets

0.15

isObject

0.15

wij

0.15

 THAN

0.15

Ø§Ø¦

0.14

 bulletin

0.14

	DECLARE

0.14

Activations Density 0.010%

references to time, specifically weeks and days

No Comments

No Known Activations