INDEX

Explanations

dates and numerical information related to events or individuals

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

-0.21

-0.19

arbon

-0.15

irez

-0.14

Û²Û°Û±

-0.14

petto

-0.14

Û²Û°Û²

-0.14

uridad

-0.14

ocale

-0.14

anst

-0.13

POSITIVE LOGITS

0.24

0.22

0.20

or

0.20

0.19

0.18

0.17

ca

0.17

Activations Density 0.054%

dates and numerical information related to events or individuals

No Comments

No Known Activations