INDEX

Explanations

references to legal and investigative terminology related to property damage in a specific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

pob

-0.15

 barric

-0.14

ories

-0.14

Hom

-0.14

 Damen

-0.14

hum

-0.14

odor

-0.13

 Coleman

-0.13

Hum

-0.13

 Bott

-0.13

POSITIVE LOGITS

 cable

0.28

 Cable

0.23

 cables

0.23

 telegram

0.20

 tele

0.19

British

0.18

telegram

0.17

igham

0.17

à¤ķà¤°à¤£

0.17

tele

0.16

Activations Density 0.023%

references to legal and investigative terminology related to property damage in a specific context

No Comments

No Known Activations