INDEX

Explanations

programming or syntax elements, specifically related to code structure

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

/rss

-0.17

apus

-0.14

zell

-0.14

lendi

-0.14

 certain

-0.14

INCLUDED

-0.14

lectron

-0.14

odia

-0.14

orer

-0.13

POSITIVE LOGITS

à¸§à¸Ļ

0.15

Fra

0.15

orsk

0.15

retry

0.15

faction

0.13

udent

0.13

rÃ©

0.13

ango

0.13

oya

0.13

cac

0.13

Activations Density 0.086%

programming or syntax elements, specifically related to code structure

No Comments

No Known Activations