INDEX

Explanations

references to personal information and consent in a privacy context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 vending

-0.16

SCO

-0.15

coma

-0.15

enk

-0.15

vation

-0.15

oe

-0.14

 poll

-0.14

 Canter

-0.14

 unregister

-0.14

vous

-0.14

POSITIVE LOGITS

 browsing

0.16

orsch

0.16

ivor

0.16

//{{

0.16

trag

0.16

íĭ´

0.15

æµ

0.15

 browse

0.15

/Input

0.15

/input

0.15

Activations Density 0.037%

references to personal information and consent in a privacy context

No Comments

No Known Activations