INDEX

Explanations

references to the concept of an "ark" or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

china

-0.16

åľ¨åľ°

-0.15

.uf

-0.14

ogr

-0.14

 Yuan

-0.14

oze

-0.14

jur

-0.14

(IServiceCollection

-0.14

çĭ¬

-0.13

ele

-0.13

POSITIVE LOGITS

ambi

0.19

toi

0.14

Ð²Ð¸Ð´

0.14

Ø±Ø§Øª

0.14

ÑĥÐ»ÑĮ

0.14

oreal

0.14

.chapter

0.14

ouser

0.13

edin

0.13

oning

0.13

Activations Density 0.007%

references to the concept of an "ark" or related terms

No Comments

No Known Activations