INDEX

Explanations

references to authority and its dominion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 ragaz

-0.19

Ð°ÑĢÐ°Ð½

-0.17

ibar

-0.15

olini

-0.15

//{{

-0.15

Fcn

-0.14

.GUI

-0.14

ego

-0.14

olina

-0.14

Probe

-0.14

POSITIVE LOGITS

 Crist

0.15

elez

0.15

 gram

0.15

 diligence

0.14

 hostel

0.14

unge

0.14

ker

0.14

eler

0.14

iversite

0.14

ÏĥÏĩ

0.13

Activations Density 0.003%

references to authority and its dominion

No Comments

No Known Activations