INDEX

Explanations

questions and invitations for reader engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

umpt

-0.17

 inquire

-0.15

ocz

-0.15

Äįka

-0.15

hora

-0.14

inst

-0.14

åº§

-0.14

Invoke

-0.14

lah

-0.13

licht

-0.13

POSITIVE LOGITS

 leave

0.35

 share

0.33

let

0.33

 Leave

0.32

 Share

0.32

Leave

0.31

leave

0.31

Share

0.30

share

0.30

 tell

0.29

Activations Density 0.040%

questions and invitations for reader engagement

No Comments

No Known Activations