INDEX

Explanations

statistics related to percentages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lash

-0.13

ovice

-0.13

amas

-0.13

-path

-0.13

amma

-0.13

ħ

-0.13

ften

-0.13

othermal

-0.13

lat

-0.13

isse

-0.13

POSITIVE LOGITS

rale

0.19

oriously

0.17

/full

0.16

lobal

0.16

éĲĺ

0.15

å·¦åı³

0.15

-plus

0.14

ake

0.14

ìĶ©

0.14

oids

0.14

Activations Density 0.016%

statistics related to percentages

No Comments

No Known Activations