INDEX

Explanations

references to military ranks and positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 karak

-0.16

 Ù¾Ø§Ø¯

-0.15

-ignore

-0.15

rani

-0.15

irit

-0.14

Gratis

-0.14

amine

-0.14

ildi

-0.14

anson

-0.14

SizeMode

-0.13

POSITIVE LOGITS

 General

0.28

 Gener

0.26

GEN

0.25

Gen

0.25

General

0.24

 Joint

0.23

eneral

0.23

Gener

0.23

 generals

0.22

Gen

0.21

Activations Density 0.067%

references to military ranks and positions

No Comments

No Known Activations