INDEX

Explanations

phrases and terms related to prohibition and restrictions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

è¦ļ

-0.16

assin

-0.15

 pairs

-0.15

Ã®

-0.15

chedulers

-0.14

wid

-0.14

igor

-0.14

ell

-0.14

 Morris

-0.13

Gi

-0.13

POSITIVE LOGITS

mlin

0.20

dden

0.19

ambi

0.17

undance

0.16

deaux

0.15

ecycle

0.15

ëĮĢíĸī

0.15

 Gros

0.15

senal

0.14

istar

0.14

Activations Density 0.009%

phrases and terms related to prohibition and restrictions

No Comments

No Known Activations