INDEX

Explanations

references to military identification and queries related to service members

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

or

-0.19

 HERE

-0.15

(?

-0.14

 perhaps

-0.14

ccd

-0.14

viz

-0.13

 Robbins

-0.13

ocking

-0.13

int

-0.13

POSITIVE LOGITS

FML

0.30

FML

0.23

#ab

0.16

 mastur

0.14

ormsg

0.14

 Ð¼Ð¸ÑĢ

0.14

_hint

0.14

auge

0.14

AIT

0.14

.gf

0.14

Activations Density 0.005%

references to military identification and queries related to service members

No Comments

No Known Activations