INDEX

Explanations

terms related to intelligence and surveillance activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 RedirectTo

-0.16

ONEY

-0.14

 spotting

-0.14

oney

-0.14

spot

-0.14

¼

-0.14

uby

-0.14

isseur

-0.14

sted

-0.14

enus

-0.14

POSITIVE LOGITS

tes

0.14

KG

0.14

tron

0.14

 mastur

0.14

uzz

0.14

olini

0.14

arella

0.13

yla

0.13

Ware

0.13

arias

0.13

Activations Density 0.023%

terms related to intelligence and surveillance activities

No Comments

No Known Activations