INDEX

Explanations

references to capacity and capacity building in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ê

-0.20

thinkable

-0.17

isnan

-0.16

mers

-0.15

Ð´Ð¶

-0.15

ÑģÑı

-0.15

conomy

-0.15

 kapit

-0.15

arily

-0.15

è´¥

-0.15

POSITIVE LOGITS

0.20

itulo

0.19

illary

0.19

utos

0.16

tn

0.15

akk

0.15

 building

0.15

aging

0.15

ench

0.15

Activations Density 0.029%

references to capacity and capacity building in various contexts

No Comments

No Known Activations