INDEX

Explanations

references to individuals or groups, particularly highlighting their roles or affiliations

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

byn

-0.15

âĢĮØ§ÙĨ

-0.15

argent

-0.14

ÑĥÐºÐ°

-0.14

dana

-0.14

uchos

-0.14

_mE

-0.14

 spou

-0.14

furt

-0.14

,application

-0.14

POSITIVE LOGITS

 former

0.24

 member

0.23

.k

0.22

 native

0.22

 frequent

0.21

 recent

0.21

 friend

0.20

 fixture

0.19

 longtime

0.19

 acquaintance

0.19

Activations Density 0.112%

references to individuals or groups, particularly highlighting their roles or affiliations

No Comments

No Known Activations