INDEX

Explanations

terms related to measurement tools and methods

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

.epam

-0.18

apur

-0.17

abouts

-0.14

deen

-0.14

ITAL

-0.14

itus

-0.14

icha

-0.14

aran

-0.14

bane

-0.14

ÎĲ

-0.14

POSITIVE LOGITS

ãĥ¬ãĤ¹

0.14

 Essentials

0.14

 sleeper

0.14

 Freed

0.14

cone

0.13

 Hogan

0.13

 Conway

0.13

ergus

0.13

Ade

0.13

Activations Density 0.721%

terms related to measurement tools and methods

No Comments

No Known Activations