INDEX

Explanations

phrases related to reading or accessing articles and stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Trot

-0.15

 Mart

-0.14

 Martin

-0.14

Spr

-0.14

áº¥t

-0.13

 Marty

-0.13

erv

-0.13

yn

-0.13

atz

-0.13

hex

-0.13

POSITIVE LOGITS

PostalCodes

0.19

RuntimeObject

0.17

 fullscreen

0.17

adm

0.16

XR

0.16

ppelin

0.15

ç¶ļ

0.15

ozem

0.15

engkap

0.15

BitFields

0.15

Activations Density 0.051%

phrases related to reading or accessing articles and stories

No Comments

No Known Activations