INDEX

Explanations

references to legal situations and law enforcement activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ãģ¡ãģ¯

-0.16

_tab

-0.16

chy

-0.15

 quang

-0.15

áº¡y

-0.14

ÄĲT

-0.14

edelta

-0.14

loat

-0.14

 Kore

-0.14

ieten

-0.14

POSITIVE LOGITS

 cooperate

0.31

 cooperation

0.31

 cooperating

0.31

 cooper

0.30

 Cooperation

0.29

 cooperative

0.29

 Cooper

0.28

 Miranda

0.25

 statements

0.24

 coop

0.23

Activations Density 0.050%

references to legal situations and law enforcement activities

No Comments

No Known Activations