INDEX

Explanations

terms related to personal information and data security

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

uil

-0.14

zac

-0.14

onomy

-0.13

 protagon

-0.13

ira

-0.13

ucer

-0.13

ocy

-0.13

atik

-0.13

avaÅŁ

-0.13

uiltin

-0.13

POSITIVE LOGITS

 Cookies

0.21

 cookies

0.21

 cookie

0.20

Our

0.20

 breach

0.19

 lawful

0.19

 Users

0.18

our

0.18

 Cookie

0.18

any

0.18

Activations Density 0.084%

terms related to personal information and data security

No Comments

No Known Activations