INDEX

Explanations

terms related to workplace safety and violations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ŀ¼

-0.15

themes

-0.14

abwe

-0.14

zion

-0.14

urile

-0.14

 Tracker

-0.13

ãĥĭãĤ¢

-0.13

apol

-0.13

 KÃ¼r

-0.13

ikler

-0.13

POSITIVE LOGITS

 Conf

0.22

 lock

0.22

 respir

0.21

 permit

0.21

 confined

0.21

 respiratory

0.21

 Lock

0.20

 Permit

0.19

 machine

0.19

 procedures

0.19

Activations Density 0.044%

terms related to workplace safety and violations

No Comments

No Known Activations