INDEX

Explanations

references to data processing challenges and solutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

å£ģ

-0.17

upal

-0.15

ipe

-0.15

Gib

-0.14

åĵ

-0.14

Convention

-0.14

erland

-0.14

ean

-0.14

tas

-0.14

iol

-0.14

POSITIVE LOGITS

 plugs

0.20

 Plug

0.19

Plug

0.19

 plug

0.18

mits

0.17

ecute

0.17

 scene

0.16

 Scene

0.16

rita

0.15

 matte

0.15

Activations Density 0.001%

references to data processing challenges and solutions

No Comments

No Known Activations