INDEX

Explanations

terms related to edibility and edible items

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

ãĥ³ãĥĸ

-0.15

gue

-0.15

malar

-0.15

ulan

-0.15

ellan

-0.14

TestFixture

-0.14

 nearly

-0.14

ÌĨ

-0.14

Ì

-0.14

.djangoproject

-0.14

POSITIVE LOGITS

owl

0.17

amar

0.16

SCALL

0.15

bjerg

0.15

Ã¡ty

0.14

 Sims

0.14

 Frauen

0.14

/il

0.14

emean

0.13

oup

0.13

Activations Density 0.003%

terms related to edibility and edible items

No Comments

No Known Activations