INDEX

Explanations

references to railway companies and related terminology

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

 carriage

-0.19

 railway

-0.15

ickets

-0.15

Ð°Ð»ÐµÐ¶

-0.14

 darm

-0.14

avig

-0.14

 metro

-0.14

 Salah

-0.14

 safezone

-0.14

ker

-0.14

POSITIVE LOGITS

GP

0.21

 repaint

0.20

 roster

0.19

 Shops

0.18

UP

0.18

 Clin

0.17

 Chess

0.17

 reef

0.17

SP

0.17

 cabo

0.17

Activations Density 0.006%

references to railway companies and related terminology

No Comments

No Known Activations