INDEX

Explanations

formal definitions and theoretical constructs typically found in academic or scientific texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ansi

-0.17

inha

-0.15

/St

-0.15

iped

-0.15

ing

-0.14

chers

-0.14

ecess

-0.14

POSITIVE LOGITS

.openConnection

0.17

ë²Į

0.15

aseline

0.15

ume

0.15

illac

0.15

blade

0.15

bage

0.14

jian

0.14

udeau

0.14

veau

0.13

Activations Density 0.035%

formal definitions and theoretical constructs typically found in academic or scientific texts

No Comments

No Known Activations