INDEX

Explanations

references to job titles and positions within organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ichel

-0.16

ersen

-0.16

ers

-0.15

Ð´ÐµÐ¼

-0.14

iyas

-0.14

rog

-0.14

 itself

-0.13

 which

-0.13

sonian

-0.13

 alone

-0.13

POSITIVE LOGITS

0.19

åħ¼

0.17

 designate

0.15

at

0.15

 chez

0.15

/editor

0.15

 à¤ıà¤µ

0.15

–

0.14

cum

0.14

Activations Density 0.077%

references to job titles and positions within organizations

No Comments

No Known Activations