INDEX

Explanations

references to academic articles and their publication details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.15

Äı

-0.14

ador

-0.14

fn

-0.14

Teh

-0.13

à¸²à¸ģ

-0.13

aya

-0.13

Eug

-0.13

 Ease

-0.13

Ð»Ð¸Ð²Ð¾

-0.13

POSITIVE LOGITS

Æ¯á»

0.20

.issue

0.17

ello

0.17

arÄ±m

0.17

à¸²à¸į

0.17

Â£Â£

0.15

AZE

0.15

================================================================================

0.15

sembly

0.14

uvw

0.14

Activations Density 0.036%

references to academic articles and their publication details

No Comments

No Known Activations