INDEX

Explanations

words related to prime or primary status, often in a ranking or importance context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 OnTrigger

-0.17

ow

-0.16

rypt

-0.15

izzato

-0.15

geben

-0.15

ugu

-0.15

ÑĢÐ°Ð·Ñĥ

-0.15

ÐµÐ·Ð´Ð°

-0.14

 Bruno

-0.14

ular

-0.14

POSITIVE LOGITS

ordial

0.22

arily

0.21

coe

0.18

rose

0.17

ply

0.16

.languages

0.16

ayi

0.16

ìĹĦ

0.16

positions

0.15

cip

0.15

Activations Density 0.011%

words related to prime or primary status, often in a ranking or importance context

No Comments

No Known Activations