INDEX

Explanations

references to local events, projects, and community-related issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

gross

-0.14

ricular

-0.14

uncated

-0.14

 Mant

-0.14

nts

-0.14

_SWAP

-0.14

ihat

-0.14

Uploaded

-0.13

 Clayton

-0.13

POSITIVE LOGITS

 Shen

0.26

ruit

0.16

pherd

0.16

 Maryland

0.15

jos

0.15

ewe

0.15

Delegate

0.14

 Worcester

0.14

urved

0.14

èĴĻ

0.14

Activations Density 0.059%

references to local events, projects, and community-related issues

No Comments

No Known Activations