INDEX

Explanations

information related to events or dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Christian

-0.29

Christ

-0.27

 Christ

-0.26

 Christians

-0.25

 Chris

-0.25

 Crist

-0.24

 Krist

-0.24

chr

-0.24

 Christie

-0.23

 christ

-0.23

POSITIVE LOGITS

 elves

0.18

naments

0.17

antz

0.17

 Joyce

0.16

//{{

0.15

 Elves

0.15

azon

0.15

interop

0.15

 gift

0.15

AdapterFactory

0.15

Activations Density 0.015%

information related to events or dates

No Comments

No Known Activations