INDEX

Explanations

coding-related terms and operations involving data handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

dda

-0.17

eras

-0.16

åĮĸ

-0.15

usc

-0.14

vic

-0.14

uuid

-0.14

 nackte

-0.14

ê¸°ëıĦ

-0.14

chest

-0.14

aid

-0.14

POSITIVE LOGITS

iesz

0.20

0.17

imed

0.16

ANNEL

0.15

bine

0.14

enville

0.14

Ð°Ð½Ð¸ÑĨ

0.14

äºĨ

0.14

Activations Density 0.026%

coding-related terms and operations involving data handling

No Comments

No Known Activations