INDEX

Explanations

references to specific functions or characteristics in a programming or data context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

erable

-0.17

rosso

-0.15

-eyed

-0.15

.gamma

-0.15

ëŁ¬ìĬ¤

-0.15

cede

-0.15

hurst

-0.15

à¤Ĥà¤¸

-0.14

insky

-0.14

akis

-0.14

POSITIVE LOGITS

olah

0.17

lesi

0.17

 Bott

0.16

menus

0.15

èµ·æĿ¥

0.14

ovid

0.14

 bott

0.14

obus

0.14

ani

0.14

 meals

0.14

Activations Density 0.001%

references to specific functions or characteristics in a programming or data context

No Comments

No Known Activations