INDEX

Explanations

numerical data and statistics relevant to companies and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ONUS

-0.17

Bez

-0.17

Za

-0.16

ArrayOf

-0.15

gable

-0.15

Dut

-0.15

 ?><?

-0.14

cyk

-0.14

-0.13

Ãªt

-0.13

POSITIVE LOGITS

 different

0.23

 distinct

0.19

ä¸įåĲĮçļĦ

0.19

different

0.18

 species

0.17

 Different

0.16

Different

0.16

 diferentes

0.16

species

0.15

_different

0.15

Activations Density 0.099%

numerical data and statistics relevant to companies and institutions

No Comments

No Known Activations