INDEX

Explanations

instances of numerical data or legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

arro

-0.17

velte

-0.16

amins

-0.15

ÙĬÙĦØ§

-0.15

ens

-0.15

olars

-0.15

 è©ķä¾¡

-0.15

holm

-0.15

atham

-0.14

iber

-0.14

POSITIVE LOGITS

LAY

0.17

Eis

0.16

 childhood

0.16

zug

0.16

ABL

0.15

Clr

0.15

rem

0.14

 ä½ĵ

0.14

 Hlav

0.14

aklÄ±

0.14

Activations Density 0.029%

instances of numerical data or legal terminology

No Comments

No Known Activations