INDEX

Explanations

content related to modifications or changes in systems or software

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

atology

-0.17

uela

-0.17

 Passive

-0.15

ÐµÐ½Ð´

-0.15

aya

-0.14

******/

-0.14

/octet

-0.14

è

-0.14

acha

-0.13

 Rita

-0.13

POSITIVE LOGITS

afen

0.19

UBLE

0.17

ial

0.17

ureau

0.16

ä¸Ī

0.16

aden

0.16

rray

0.16

tti

0.15

ded

0.15

ewise

0.15

Activations Density 0.011%

content related to modifications or changes in systems or software

No Comments

No Known Activations