INDEX

Explanations

terms related to programming, specifically around rendering and processing in templates

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

.nih

-0.17

isy

-0.16

pte

-0.16

ucci

-0.15

 glare

-0.14

ifie

-0.14

ESS

-0.14

esy

-0.14

eless

-0.14

actories

-0.14

POSITIVE LOGITS

_BASIC

0.17

landa

0.17

itsu

0.16

innacle

0.15

beros

0.15

andel

0.15

Lex

0.14

 discarded

0.14

avad

0.14

 Francie

0.14

Activations Density 0.156%

terms related to programming, specifically around rendering and processing in templates

No Comments

No Known Activations