INDEX

Explanations

structured numerical data related to measurements or dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

illard

-0.17

akh

-0.16

illon

-0.16

ãĤµãĤ¤

-0.14

wner

-0.14

 Colbert

-0.14

à¤ķ

-0.14

ÄĽk

-0.14

uxt

-0.14

POSITIVE LOGITS

 vivo

0.15

ipp

0.15

andre

0.15

ones

0.15

 Crowley

0.15

ONES

0.14

<source

0.14

fur

0.14

ovic

0.14

anon

0.14

Activations Density 0.011%

structured numerical data related to measurements or dimensions

No Comments

No Known Activations