INDEX

Explanations

qualifiers and modifiers that indicate emphasis or degree

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

uje

-0.16

okud

-0.14

eden

-0.14

avier

-0.13

ikal

-0.13

à¹ģà¸Ļ

-0.13

çīĽ

-0.13

Ø´ÙĨØ¨Ùĩ

-0.13

udi

-0.13

aint

-0.13

POSITIVE LOGITS

the

0.20

0.19

an

0.15

ehr

0.15

our

0.14

 those

0.14

 another

0.14

inton

0.14

 three

0.14

veral

0.14

Activations Density 0.227%

qualifiers and modifiers that indicate emphasis or degree

No Comments

No Known Activations