INDEX

Explanations

prepositions and phrases indicating location or participation in activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

alley

-0.14

 danmark

-0.13

ddit

-0.13

styleType

-0.13

 compte

-0.13

ÑĢÑĥÑģ

-0.13

áº¬

-0.12

all

-0.12

ÑĪÐºÐ¸

-0.12

ulton

-0.12

POSITIVE LOGITS

-the

0.41

the

0.36

_the

0.33

the

0.30

thew

0.28

the

0.26

THE

0.25

.the

0.24

thes

0.23

-The

0.23

Activations Density 0.283%

prepositions and phrases indicating location or participation in activities

No Comments

No Known Activations