INDEX

Explanations

references to military activities and territorial conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

acin

-0.17

.scalablytyped

-0.15

phem

-0.15

iris

-0.15

amble

-0.15

uncate

-0.15

xsi

-0.14

 Bellev

-0.14

olem

-0.14

anco

-0.14

POSITIVE LOGITS

ometr

0.16

ext

0.16

 traces

0.16

 committed

0.15

 Wagner

0.15

ÑĨÐµÑģ

0.15

 Robertson

0.14

Ing

0.14

 prelim

0.14

 liquid

0.14

Activations Density 0.008%

references to military activities and territorial conflicts

No Comments

No Known Activations