INDEX

Explanations

coding terms related to setup and execution 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 @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

gap

-0.15

abar

-0.14

mage

-0.14

ewood

-0.14

.Migrations

-0.14

Increment

-0.14

Caj

-0.14

 sayÄ±lÄ±

-0.14

åĢĴ

-0.13

urs

-0.13

POSITIVE LOGITS

agina

0.17

ueur

0.14

 Ð½Ð°ÑıÐ²

0.14

ãĥĪãĥª

0.14

 rowspan

0.14

.setUp

0.14

phinx

0.13

ÑħÐ¸

0.13

abcdefghijklmnop

0.13

Activations Density 0.004%

coding terms related to setup and execution in programming

No Comments

No Known Activations