INDEX

Explanations

references to specific locations and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 kÃ¥

-0.17

unc

-0.15

Unc

-0.15

pora

-0.14

 Uncomment

-0.14

tar

-0.14

seb

-0.14

abei

-0.14

oz

-0.14

 nackte

-0.14

POSITIVE LOGITS

 Rock

0.22

 Bureau

0.21

 Prophet

0.19

 Stre

0.19

 ROCK

0.19

rock

0.18

Rock

0.18

 Arsenal

0.17

 Sterling

0.17

 rock

0.17

Activations Density 0.004%

references to specific locations and entities

No Comments

No Known Activations