INDEX

Explanations

phrases and concepts related to "winning" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

tes

-0.20

vore

-0.16

/or

-0.16

als

-0.15

uteur

-0.15

EB

-0.15

zent

-0.14

duct

-0.14

kov

-0.14

ìĤ¬íķŃ

-0.13

POSITIVE LOGITS

nable

0.20

-win

0.16

now

0.16

throp

0.14

amaÃ±o

0.14

riminator

0.14

/win

0.14

ingly

0.14

NF

0.13

agli

0.13

Activations Density 0.067%

phrases and concepts related to "winning" in various contexts

No Comments

No Known Activations