INDEX

Explanations

queries and specific commands related to data manipulation or programming tasks

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

ibling

-0.13

alogy

-0.13

usi

-0.13

 Bain

-0.13

owell

-0.13

ense

-0.13

ie

-0.13

cla

-0.13

æµ´

-0.13

.arg

-0.13

POSITIVE LOGITS

urger

0.15

erate

0.15

licted

0.15

ÐºÐ°Ð¶

0.14

Ã¤l

0.14

adar

0.13

asher

0.13

ÐĽÐ¬

0.13

«

0.13

Activations Density 0.062%

queries and specific commands related to data manipulation or programming tasks

No Comments

No Known Activations