INDEX

Explanations

quantities or counts of objects or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

-0.15

chÃ¡z

-0.14

iente

-0.14

chal

-0.14

meld

-0.14

abin

-0.14

oute

-0.14

idor

-0.14

lier

-0.13

POSITIVE LOGITS

ë°ĺ

0.14

 VÅ¡

0.14

/Sub

0.14

asaki

0.14

 Ð¿ÑĢÐ¾ÑĨ

0.13

inet

0.13

iaux

0.13

oard

0.13

QUIRES

0.13

ertainment

0.13

Activations Density 0.024%

quantities or counts of objects or entities

No Comments

No Known Activations