INDEX

Explanations

indicators of growth and improvement in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

MSN

-0.17

gro

-0.16

Ð¸

-0.16

klad

-0.15

abar

-0.15

Pie

-0.15

adam

-0.14

sub

-0.14

kins

-0.14

 indeed

-0.14

POSITIVE LOGITS

 weitere

0.21

 further

0.21

 ná»¯a

0.20

 weiter

0.18

urther

0.17

è¿Ľä¸ĢæŃ¥

0.16

chio

0.16

thers

0.15

itere

0.15

ockey

0.15

Activations Density 0.138%

indicators of growth and improvement in various contexts

No Comments

No Known Activations