INDEX

Explanations

terms related to motorcycles and motorcycle gear

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 subscribing

-0.14

 innocence

-0.14

 pros

-0.14

 democr

-0.14

 quarter

-0.14

Va

-0.14

 Pros

-0.13

 dece

-0.13

“

-0.13

POSITIVE LOGITS

ħ

0.17

tÃŃ

0.15

erten

0.15

unas

0.15

_intent

0.14

Laugh

0.14

 NDEBUG

0.14

uggage

0.14

.scalablytyped

0.13

ÑĸÐ½Ð¾

0.13

Activations Density 0.003%

terms related to motorcycles and motorcycle gear

No Comments

No Known Activations