INDEX

Explanations

references to job positions and organizational structures

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

borg

-0.17

 Mode

-0.15

Ð°ÑĢÐ´

-0.14

ëł¨

-0.14

amble

-0.14

ifr

-0.13

æĴ

-0.13

mode

-0.13

ew

-0.13

 mode

-0.13

POSITIVE LOGITS

elpers

0.16

aty

0.15

already

0.15

à¸¡à¸Ļà¸ķà¸£

0.15

 already

0.14

ocumented

0.14

inx

0.14

ÐĵÐŀ

0.14

nano

0.14

\CMS

0.14

Activations Density 0.074%

references to job positions and organizational structures

No Comments

No Known Activations