INDEX

Explanations

technical terms and identifiers related to data modeling in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ieten

-0.16

ives

-0.15

-mouth

-0.15

ying

-0.15

 VÃ¡c

-0.15

llen

-0.15

ersen

-0.15

iew

-0.14

ucken

-0.14

tach

-0.14

POSITIVE LOGITS

 clearance

0.15

'])){

0.14

 xOffset

0.14

å¼Ħ

0.14

WithMany

0.14

ĶĦ

0.14

íĬľ

0.14

clr

0.13

 IsNot

0.13

è³

0.13

Activations Density 0.032%

technical terms and identifiers related to data modeling in a programming context

No Comments

No Known Activations