INDEX

Explanations

words related to scientific concepts and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ings

-0.21

eds

-0.20

ing

-0.18

inh

-0.18

nings

-0.18

uky

-0.17

ING

-0.17

ÂŃing

-0.16

INGS

-0.16

ups

-0.15

POSITIVE LOGITS

ated

0.56

ating

0.54

ATED

0.40

ATING

0.38

ate

0.34

ators

0.34

ator

0.31

ation

0.31

ates

0.30

ATE

0.28

Activations Density 0.105%

words related to scientific concepts and terminology

No Comments

No Known Activations