INDEX

Explanations

prepositions and phrases indicating relationships or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 latter

-0.17

dev

-0.15

dev

-0.15

_AND

-0.14

TO

-0.14

To

-0.14

Ø§Ø±Ø´

-0.14

 Selection

-0.14

Ø±ÙĪÙħ

-0.13

å¤§äºº

-0.13

POSITIVE LOGITS

gether

0.30

atre

0.26

0.23

oled

0.22

/-

0.21

odore

0.20

ir

0.20

ory

0.20

0.19

–

0.19

Activations Density 0.052%

prepositions and phrases indicating relationships or connections

No Comments

No Known Activations