INDEX

Explanations

references to different formats or types of media or content delivery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

hots

-0.14

bette

-0.14

zion

-0.14

 filmer

-0.14

unik

-0.13

order

-0.13

íĹĪ

-0.13

 ordering

-0.13

aphrag

-0.13

holm

-0.13

POSITIVE LOGITS

 English

0.22

 formats

0.22

 batches

0.21

pdf

0.21

 sets

0.21

 install

0.21

 english

0.21

PDF

0.20

 booklet

0.19

 stages

0.19

Activations Density 0.175%

references to different formats or types of media or content delivery

No Comments

No Known Activations