INDEX

Explanations

phrases and terms related to caregiving

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

ondere

-0.18

ropol

-0.17

mith

-0.17

artin

-0.17

sher

-0.17

ski

-0.17

burgh

-0.16

rup

-0.16

swick

-0.16

sis

-0.16

POSITIVE LOGITS

fully

0.32

free

0.30

ening

0.25

full

0.25

lessly

0.25

ful

0.24

lessness

0.24

ering

0.22

ismatic

0.22

FULL

0.21

Activations Density 0.013%

phrases and terms related to caregiving

No Comments

No Known Activations