INDEX

Explanations

instances of surprise or unexpected outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ertino

-0.17

erty

-0.16

egas

-0.15

akens

-0.15

noun

-0.15

å²³

-0.15

emony

-0.14

inecraft

-0.14

bohydr

-0.14

eus

-0.14

POSITIVE LOGITS

(Me

0.15

och

0.15

Mei

0.14

odon

0.14

ering

0.14

ault

0.14

 æľĿ

0.14

atos

0.13

TouchEvent

0.13

ÐµÐ¼Ð°

0.13

Activations Density 0.208%

instances of surprise or unexpected outcomes

No Comments

No Known Activations