INDEX

Explanations

references to biological concepts and studies, particularly in the context of academic publishing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

abelle

-0.19

aneous

-0.16

ope

-0.16

vore

-0.16

ase

-0.15

ugs

-0.15

ullan

-0.15

ĨĴ

-0.15

ere

-0.15

opa

-0.15

POSITIVE LOGITS

jamin

0.27

quets

0.20

.gdx

0.19

emer

0.19

iful

0.18

itters

0.17

friend

0.17

ckett

0.17

elor

0.17

ardo

0.17

Activations Density 2.344%

references to biological concepts and studies, particularly in the context of academic publishing

No Comments

No Known Activations