INDEX

Explanations

occurrences of traffic-related terms and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

htag

-0.16

zdy

-0.15

æĲ

-0.14

MATCH

-0.14

adaÅŁ

-0.14

ãģ£ãģ±

-0.14

è¨Ģ

-0.14

IGGER

-0.14

@show

-0.14

 matches

-0.14

POSITIVE LOGITS

 Turns

0.24

 chic

0.22

 straight

0.22

ess

0.22

 corners

0.21

 Turn

0.21

 turns

0.20

 pits

0.20

straight

0.19

 turn

0.19

Activations Density 0.020%

occurrences of traffic-related terms and measurements

No Comments

No Known Activations