INDEX

Explanations

phrases related to legal notices and privacy policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

jen

-0.14

.semantic

-0.14

.uf

-0.13

 Ð¸Ð¼Ðµ

-0.13

 Plenty

-0.13

Then

-0.13

UPPORT

-0.13

 gÃ¶re

-0.13

 RELATED

-0.13

inan

-0.13

POSITIVE LOGITS

 Except

0.27

Except

0.26

 Unless

0.24

 except

0.23

 unless

0.23

except

0.21

Unless

0.20

 Should

0.20

 Please

0.20

unless

0.19

Activations Density 0.076%

phrases related to legal notices and privacy policies

No Comments

No Known Activations