INDEX

Explanations

proper nouns, names, and titles of organizations or companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Also

-0.14

 Also

-0.14

 passes

-0.13

 intersects

-0.13

fails

-0.13

ined

-0.13

afs

-0.12

_UNUSED

-0.12

icularly

-0.12

ih

-0.12

POSITIVE LOGITS

æĺ¯ä¸Ģä¸ª

0.29

æĺ¯æĪĳ

0.29

is

0.29

 adalah

0.28

æĺ¯ä¸Ģ

0.27

was

0.26

 æĺ¯

0.25

 merupakan

0.24

 ÑıÐ²Ð»ÑıÐµÑĤÑģÑı

0.23

æĺ¯ä¸ª

0.23

Activations Density 0.310%

proper nouns, names, and titles of organizations or companies

No Comments

No Known Activations