INDEX

Explanations

personal pronouns and expressions of personal opinion or feelings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Î»Ïį

-0.14

ajs

-0.14

uzu

-0.13

åħ¹

-0.13

amburger

-0.13

 Potential

-0.13

//{{

-0.13

umbs

-0.13

uster

-0.13

 tane

-0.13

POSITIVE LOGITS

 feeling

0.27

 impression

0.27

 experience

0.24

gut

0.24

 understanding

0.23

 colleague

0.21

 experiences

0.21

 concern

0.20

 observation

0.20

own

0.20

Activations Density 0.156%

personal pronouns and expressions of personal opinion or feelings

No Comments

No Known Activations