INDEX

Explanations

quantities or groupings, particularly focusing on numbers and statistical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ourn

-0.17

 lagi

-0.15

Hij

-0.15

ijo

-0.14

oned

-0.14

-0.13

ud

-0.13

intern

-0.13

omb

-0.13

ambda

-0.13

POSITIVE LOGITS

GBK

0.16

arehouse

0.16

czy

0.16

imson

0.15

quip

0.15

avenport

0.15

 Sender

0.15

odge

0.14

esome

0.14

cona

0.14

Activations Density 0.137%

quantities or groupings, particularly focusing on numbers and statistical data

No Comments

No Known Activations