INDEX

Explanations

references to various types of lists in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

istas

-0.17

pany

-0.16

izon

-0.15

imps

-0.15

lest

-0.15

steen

-0.15

hausen

-0.14

éĩı

-0.14

OWN

-0.14

POSITIVE LOGITS

eners

0.33

ings

0.30

icle

0.28

ened

0.26

ening

0.24

-unstyled

0.23

rik

0.21

icles

0.21

erner

0.20

agem

0.20

Activations Density 0.054%

references to various types of lists in the text

No Comments

No Known Activations