INDEX

Explanations

references to expectations and clarity in communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

fal

-0.16

 Carlson

-0.15

emas

-0.15

åĶ

-0.15

-0.14

tr

-0.14

sat

-0.14

 whim

-0.14

POSITIVE LOGITS

uthor

0.15

ouden

0.15

iless

0.15

Ã¡nh

0.14

olicy

0.14

udeau

0.14

tsy

0.14

itsu

0.14

bjerg

0.14

 ÐµÑģÑĤÐµ

0.14

Activations Density 0.166%

references to expectations and clarity in communication

No Comments

No Known Activations