INDEX

Explanations

elements and actions related to writing and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

oro

-0.16

abr

-0.16

irr

-0.15

itters

-0.15

 handwritten

-0.15

 à¤ħà¤ķ

-0.14

 caps

-0.14

ago

-0.14

Archive

-0.14

shaw

-0.14

POSITIVE LOGITS

 slips

0.28

 ruled

0.26

pad

0.26

 index

0.24

 Post

0.24

 lined

0.23

 scrap

0.23

 pads

0.23

index

0.22

 slip

0.22

Activations Density 0.104%

elements and actions related to writing and documentation

No Comments

No Known Activations