INDEX

Explanations

references to published books and their distribution

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

Ð±Ð¸Ð½Ð°

-0.15

clo

-0.15

clo

-0.14

 bottled

-0.14

 diary

-0.13

 Curtain

-0.13

ati

-0.13

administrator

-0.13

è¿ĩ

-0.13

ricks

-0.13

POSITIVE LOGITS

 distrib

0.18

 distribution

0.17

ibox

0.17

 Distribution

0.17

 Distrib

0.17

distribution

0.17

 Distributed

0.16

iej

0.16

Distribution

0.16

 distribute

0.16

Activations Density 0.146%

references to published books and their distribution

No Comments

No Known Activations