INDEX

Explanations

common English function words and phrases conveying basic actions or states

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

 æı

-0.15

odem

-0.14

umpy

-0.14

LAY

-0.14

Ä

-0.14

Ð½Ð°ÑĢ

-0.13

\Lib

-0.13

 Desk

-0.13

\common

-0.13

cip

-0.13

POSITIVE LOGITS

ignon

0.19

inton

0.18

uma

0.17

voie

0.15

iers

0.14

uku

0.14

ency

0.14

Â¸

0.14

anism

0.14

irth

0.14

Activations Density 0.002%

common English function words and phrases conveying basic actions or states

No Comments

No Known Activations