INDEX

Explanations

technical terms and concepts related to programming and memory management

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

ijn

-0.17

 Surprise

-0.15

ell

-0.15

 folklore

-0.15

 folk

-0.15

 surprise

-0.14

ora

-0.14

etro

-0.14

Ell

-0.14

ella

-0.14

POSITIVE LOGITS

coil

0.15

ãĥ¼ãĥī

0.15

tog

0.14

Ã©r

0.14

adem

0.13

celik

0.13

esteem

0.13

nech

0.13

 relent

0.13

lish

0.13

Activations Density 0.033%

technical terms and concepts related to programming and memory management

No Comments

No Known Activations