INDEX

Explanations

phrases related to letting go or release

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

stery

-0.16

 nutshell

-0.15

rna

-0.15

surname

-0.14

 chez

-0.14

ÑĢÐ°Ñħ

-0.14

ucc

-0.14

Markup

-0.14

icot

-0.14

strate

-0.14

POSITIVE LOGITS

 loose

0.40

tings

0.32

 Loose

0.30

 slip

0.28

go

0.28

ting

0.27

down

0.26

tres

0.24

rip

0.24

-go

0.23

Activations Density 0.038%

phrases related to letting go or release

No Comments

No Known Activations