INDEX

Explanations

titles and positions related to government or public service

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ovie

-0.15

quer

-0.15

bole

-0.15

ÑĸÑĩ

-0.15

iem

-0.15

 Sist

-0.14

human

-0.14

 human

-0.14

uman

-0.13

oru

-0.13

POSITIVE LOGITS

amate

0.15

enna

0.14

atter

0.14

ÃŃr

0.14

amment

0.14

ushman

0.14

aw

0.13

awah

0.13

Activations Density 0.011%

titles and positions related to government or public service

No Comments

No Known Activations

titles and positions related to government or public service

No Comments

No Known Activations