INDEX

Explanations

statistical differences and analysis in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Cutter

-0.18

ysl

-0.14

mere

-0.14

Ã¡ty

-0.14

morph

-0.14

ãĥ³ãĥĸ

-0.13

 Obst

-0.13

DEF

-0.13

MAS

-0.13

linger

-0.13

POSITIVE LOGITS

Ã³nico

0.17

erin

0.16

acket

0.15

istrov

0.14

lient

0.14

erged

0.14

ackle

0.14

 khÃŃ

0.14

liga

0.13

INVAL

0.13

Activations Density 0.062%

statistical differences and analysis in data

No Comments

No Known Activations

statistical differences and analysis in data

No Comments

No Known Activations