INDEX

Explanations

expressions of willingness to assist or provide help

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

iedo

-0.17

allah

-0.17

oldem

-0.16

pest

-0.16

affle

-0.16

nist

-0.16

´Ī

-0.14

iye

-0.14

usz

-0.14

èĬĿ

-0.14

POSITIVE LOGITS

 happy

0.34

 Happy

0.31

happy

0.30

 happiness

0.30

Happy

0.30

 pleasure

0.29

 glad

0.29

 Glad

0.29

 HAPP

0.26

 Happiness

0.24

Activations Density 0.105%

expressions of willingness to assist or provide help

No Comments

No Known Activations