INDEX

Explanations

terms related to minimalism and efficiency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

DF

-0.16

reuse

-0.15

iesz

-0.15

ê³Ħ

-0.14

Het

-0.14

 meis

-0.14

viso

-0.14

 dword

-0.14

ehler

-0.14

ysl

-0.13

POSITIVE LOGITS

 cost

0.16

 costs

0.16

 Costs

0.16

(<

0.15

 Cost

0.15

 risk

0.15

acket

0.15

ÎŃÎ»

0.15

andbox

0.14

-cost

0.14

Activations Density 0.073%

terms related to minimalism and efficiency

No Comments

No Known Activations