INDEX

Explanations

expressions of accountability and criticism towards governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Pub

-0.15

aza

-0.15

ocht

-0.15

 thereby

-0.15

odem

-0.14

eger

-0.14

pection

-0.14

bÃŃr

-0.14

éĺµ

-0.14

Trivia

-0.13

POSITIVE LOGITS

 equally

0.24

tro

0.18

 troop

0.18

@Resource

0.17

bags

0.16

xCA

0.16

 chor

0.15

imoto

0.15

Tro

0.15

Activations Density 0.103%

expressions of accountability and criticism towards governance

No Comments

No Known Activations