INDEX

Explanations

references to specific geographic locations and demographic data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

eldon

-0.17

.scalablytyped

-0.16

orsch

-0.16

Ã©nÃ©

-0.15

ouser

-0.14

ÙĪÙĦØ§Øª

-0.14

arrass

-0.14

assa

-0.14

abbo

-0.14

POSITIVE LOGITS

ona

0.15

JM

0.15

SDK

0.14

 precedence

0.14

CT

0.14

acious

0.14

iale

0.14

 partners

0.13

 near

0.13

 Apple

0.13

Activations Density 0.007%

references to specific geographic locations and demographic data

No Comments

No Known Activations