INDEX

Explanations

words related to functionality and effectiveness in systems or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 à¹Ĩ

-0.15

ockey

-0.15

cket

-0.15

ermint

-0.14

adele

-0.14

affen

-0.14

zing

-0.14

 Malone

-0.14

Republic

-0.14

Disposed

-0.14

POSITIVE LOGITS

 itself

0.22

 thems

0.15

ONO

0.15

akedown

0.14

 çµĲ

0.14

ebek

0.14

 Cust

0.14

BOR

0.14

avin

0.13

MED

0.13

Activations Density 0.273%

words related to functionality and effectiveness in systems or processes

No Comments

No Known Activations