INDEX

Explanations

terms related to motorcycle helmets and safety gear

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

endl

-0.16

MESS

-0.15

umed

-0.15

 ê¼

-0.14

acci

-0.14

á»Ńa

-0.14

igar

-0.14

kte

-0.14

umes

-0.14

actories

-0.14

POSITIVE LOGITS

ingo

0.17

omb

0.16

ProcessEvent

0.15

 Owens

0.14

/schema

0.14

thag

0.13

 spit

0.13

erset

0.13

AXB

0.13

 anzeigen

0.13

Activations Density 0.073%

terms related to motorcycle helmets and safety gear

No Comments

No Known Activations