INDEX

Explanations

mathematical notation related to functions and integrals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

inia

-0.15

invisible

-0.14

uling

-0.14

Enlarge

-0.14

ì§

-0.14

Dag

-0.14

zel

-0.14

Roh

-0.13

ãĥ¬ãĥ³

-0.13

iju

-0.13

POSITIVE LOGITS

dt

0.23

dt

0.21

outh

0.17

 differential

0.15

.dt

0.15

èĽ

0.15

structural

0.14

und

0.14

ifferential

0.14

 structural

0.14

Activations Density 0.075%

mathematical notation related to functions and integrals

No Comments

No Known Activations