INDEX

Explanations

phrases and terms related to legality and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ã¤t

-0.16

raman

-0.14

BLUE

-0.14

 Leisure

-0.14

áº£y

-0.14

 silver

-0.14

 Atlantis

-0.14

uo

-0.14

less

-0.13

POSITIVE LOGITS

spiel

0.18

AndView

0.17

hausen

0.15

agens

0.15

itten

0.15

osy

0.14

MUX

0.14

oses

0.14

verbatim

0.14

zent

0.14

Activations Density 0.241%

phrases and terms related to legality and regulations

No Comments

No Known Activations