INDEX

Explanations

references to personal injuries and compensation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ENCIL

-0.16

ç¸¾

-0.14

-REAL

-0.14

ivatel

-0.14

enta

-0.14

 ê·

-0.13

wright

-0.13

 Ð·Ð°Ð±Ð¾Ð»ÐµÐ²Ð°Ð½Ð¸Ð¹

-0.13

ì§ľ

-0.13

éĻµ

-0.13

POSITIVE LOGITS

 accident

0.26

 insurance

0.25

PIP

0.23

 injuries

0.22

 Insurance

0.22

 Accident

0.22

Insurance

0.21

 collision

0.21

 crash

0.21

 injured

0.21

Activations Density 0.050%

references to personal injuries and compensation processes

No Comments

No Known Activations