INDEX

Explanations

references to time, specifically relating to past events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 YEARS

-0.15

later

-0.15

 frÃ¼

-0.15

 later

-0.15

iasm

-0.14

longleftrightarrow

-0.14

LATED

-0.14

 tableau

-0.13

specifier

-0.13

ãģıãģł

-0.13

POSITIVE LOGITS

ago

0.35

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.24

 when

0.23

-present

0.21

/month

0.21

 during

0.20

-end

0.20

/current

0.19

(before

0.18

/right

0.18

Activations Density 0.114%

references to time, specifically relating to past events

No Comments

No Known Activations