INDEX

Explanations

references to military ranks and roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

atoire

-0.14

ifferential

-0.14

 Premi

-0.14

icit

-0.14

ANTE

-0.14

åıĤçħ§

-0.14

ê°Ŀ

-0.14

ulan

-0.13

SizeMode

-0.13

Cly

-0.13

POSITIVE LOGITS

 General

0.30

 Gener

0.25

 generals

0.25

General

0.25

eneral

0.24

 command

0.24

 commands

0.23

adm

0.22

Gener

0.22

 general

0.22

Activations Density 0.120%

references to military ranks and roles

No Comments

No Known Activations