INDEX

Explanations

phrases indicating participation or involvement in activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ø¯ÙĪ

-0.16

appable

-0.15

SCALL

-0.15

ydk

-0.14

 ÑĥÐ´

-0.14

avax

-0.14

argins

-0.14

addons

-0.13

 ConnectionState

-0.13

urdy

-0.13

POSITIVE LOGITS

leta

0.16

0.15

0.14

 ration

0.14

enced

0.14

 activities

0.14

uming

0.14

0.13

CSR

0.13

Activations Density 0.048%

phrases indicating participation or involvement in activities

No Comments

No Known Activations