INDEX

Explanations

phrases that indicate time references, specifically relating to days and specific temporal markers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

setter

-0.16

 Dawn

-0.15

 Sense

-0.14

 Rounds

-0.14

illum

-0.14

 knock

-0.14

Sense

-0.14

Ð²Ð¸Ð´

-0.14

-0.13

ikon

-0.13

POSITIVE LOGITS

 year

0.23

year

0.20

ardy

0.19

 nÄĥm

0.18

annÃ©e

0.18

_YEAR

0.17

arde

0.17

.year

0.17

day

0.17

 evening

0.17

Activations Density 0.055%

phrases that indicate time references, specifically relating to days and specific temporal markers

No Comments

No Known Activations