INDEX

Explanations

references to personal coaching and training support systems

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

_Internal

-0.17

leck

-0.16

ohan

-0.15

edla

-0.15

erland

-0.14

acr

-0.14

ffer

-0.13

kla

-0.13

uced

-0.13

odon

-0.13

POSITIVE LOGITS

 individual

0.35

 face

0.32

One

0.30

 Individual

0.29

 private

0.29

-One

0.29

 personal

0.29

one

0.28

-one

0.27

 personalized

0.26

Activations Density 0.212%

references to personal coaching and training support systems

No Comments

No Known Activations