INDEX

Explanations

technical terms related to operations and processes in programming

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

 dipl

-0.17

ÐµÑģÑĤÐ²

-0.17

.effects

-0.16

ãĥ¼ãĥ©

-0.15

antt

-0.14

Bid

-0.14

omanip

-0.14

à¹Ģà¸£

-0.14

 diplom

-0.14

ceso

-0.14

POSITIVE LOGITS

ally

0.16

ãģıãĤī

0.16

Īëĭ¤

0.16

ëŁī

0.15

aba

0.15

 bass

0.15

ikk

0.14

 Cart

0.14

 Transit

0.14

Sor

0.14

Activations Density 0.027%

technical terms related to operations and processes in programming

No Comments

No Known Activations