INDEX

Explanations

patterns of increasing amounts or qualities, highlighting comparative relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

YTE

-0.16

igkeit

-0.16

èĥİ

-0.15

ute

-0.14

ucker

-0.14

ouis

-0.14

vÃ½

-0.14

kke

-0.13

LAP

-0.13

¢åįķ

-0.13

POSITIVE LOGITS

 chances

0.17

 likelihood

0.16

 odds

0.16

ObjectId

0.15

verse

0.14

ackle

0.14

ëĳ¥

0.14

jis

0.14

 Ð´Ð¾Ð²

0.14

-sensitive

0.14

Activations Density 0.019%

patterns of increasing amounts or qualities, highlighting comparative relationships

No Comments

No Known Activations