INDEX

Explanations

references to specific programming components or structures related to data storage and management

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

orton

-0.16

pagen

-0.14

unj

-0.14

ucken

-0.14

ungan

-0.14

lys

-0.14

isses

-0.14

ijken

-0.14

ong

-0.14

eyse

-0.13

POSITIVE LOGITS

ä»ģ

0.16

ÑĢÐµÐ´Ð¸ÑĤ

0.15

à¸Ķà¸¢

0.14

ced

0.14

ÐµÐ²Ð¸Ð´

0.14

eut

0.13

.units

0.13

 fitte

0.13

.office

0.13

iced

0.13

Activations Density 0.030%

references to specific programming components or structures related to data storage and management

No Comments

No Known Activations