INDEX

Explanations

names and identifiers associated with people, places, or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ients

-0.16

amework

-0.15

geries

-0.15

eer

-0.14

agements

-0.14

encies

-0.14

OX

-0.14

APO

-0.14

utschein

-0.14

cribe

-0.14

POSITIVE LOGITS

odore

0.29

atre

0.26

adays

0.26

etheless

0.21

gether

0.19

phalt

0.18

west

0.17

tlement

0.17

/-

0.17

lectual

0.17

Activations Density 0.421%

names and identifiers associated with people, places, or organizations

No Comments

No Known Activations