INDEX

Explanations

references to statistical data regarding pregnancies and healthcare metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-addon

-0.15

baugh

-0.15

.localization

-0.15

ninger

-0.14

agra

-0.14

ÑĪÐµÐ²

-0.14

alleries

-0.14

 Kraj

-0.14

orf

-0.13

lessons

-0.13

POSITIVE LOGITS

urette

0.17

erti

0.14

erman

0.14

rib

0.14

afari

0.14

é®

0.14

orns

0.13

ighton

0.13

Pr

0.13

 Duck

0.13

Activations Density 0.014%

references to statistical data regarding pregnancies and healthcare metrics

No Comments

No Known Activations