INDEX

Explanations

references to different options and alternatives in a discussion or context

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

foon

-0.17

roll

-0.17

orer

-0.16

urgeon

-0.16

oras

-0.15

poons

-0.15

OperationException

-0.15

anta

-0.14

<Option

-0.14

POSITIVE LOGITS

ality

0.29

nal

0.26

als

0.22

ally

0.21

nel

0.20

:selected

0.19

ning

0.19

naires

0.18

ALLY

0.18

ated

0.17

Activations Density 0.058%

references to different options and alternatives in a discussion or context

No Comments

No Known Activations