INDEX

Explanations

technical terms and structured references related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Hindered

-0.17

ingu

-0.15

anka

-0.15

elic

-0.15

iba

-0.14

 Hanson

-0.14

vu

-0.14

iesz

-0.14

aeda

-0.14

iali

-0.14

POSITIVE LOGITS

ullan

0.14

oland

0.14

Jr

0.14

zcze

0.14

 Mais

0.13

Mate

0.13

lin

0.13

papers

0.13

_lite

0.13

Activations Density 0.689%

technical terms and structured references related to programming and software development

No Comments

No Known Activations