INDEX

Explanations

words related to biological measurements and assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ivate

-0.19

àµį

-0.19

iment

-0.16

pitch

-0.16

.scalablytyped

-0.16

ikut

-0.16

 Mell

-0.15

ician

-0.15

pri

-0.15

ivism

-0.15

POSITIVE LOGITS

orphic

0.27

orph

0.27

etric

0.27

ycin

0.25

orphism

0.23

agnet

0.23

etry

0.21

agnetic

0.21

olecular

0.21

inded

0.20

Activations Density 0.100%

words related to biological measurements and assessments

No Comments

No Known Activations