INDEX

Explanations

words and phrases related to legal charges and criminal activity

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

ambre

-0.17

 stump

-0.15

 murders

-0.15

arget

-0.15

_CF

-0.14

orgen

-0.14

abay

-0.14

essler

-0.14

Ø§ÛĮ

-0.13

nap

-0.13

POSITIVE LOGITS

 Disorder

0.23

 disorder

0.23

 Poss

0.23

 possession

0.21

hind

0.19

 Resist

0.19

peater

0.19

 Battery

0.18

 resisting

0.17

Poss

0.17

Activations Density 0.030%

words and phrases related to legal charges and criminal activity

No Comments

No Known Activations