INDEX

Explanations

terms related to scientific analysis and experimental results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Sto

-0.16

ingham

-0.15

Recognizer

-0.15

å´

-0.15

sto

-0.15

ippet

-0.14

structuring

-0.13

nev

-0.13

lassian

-0.13

ë²Ī

-0.13

POSITIVE LOGITS

olik

0.17

kola

0.15

ÙĨØ§ÙĨ

0.14

 canvas

0.14

rych

0.14

via

0.14

 liner

0.14

 magna

0.14

olin

0.14

enci

0.14

Activations Density 0.060%

terms related to scientific analysis and experimental results

No Comments

No Known Activations