INDEX

Explanations

phrases that emphasize interesting or lesser-known facts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ð»ÑĥÑĩ

-0.14

 Bhar

-0.14

utorial

-0.13

ex

-0.13

æĭħ

-0.13

.indices

-0.13

apor

-0.13

 witnesses

-0.13

åģľ

-0.13

 signature

-0.13

POSITIVE LOGITS

 facts

0.36

 Facts

0.32

facts

0.31

 Fact

0.27

 fact

0.27

_fact

0.25

FACT

0.25

 ÑĦÐ°ÐºÑĤ

0.24

Fact

0.24

 FACT

0.23

Activations Density 0.057%

phrases that emphasize interesting or lesser-known facts

No Comments

No Known Activations