INDEX

Explanations

mentions of advertisements or promotional content

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

itzer

-0.15

ernen

-0.15

ENDER

-0.15

 uÃ§

-0.15

uction

-0.14

erness

-0.14

Ð¾Ð¼ÐµÑĢ

-0.14

dling

-0.14

uded

-0.14

 ÑĢÐµÐ±

-0.14

POSITIVE LOGITS

ity

0.25

rien

0.22

el

0.22

rian

0.21

nan

0.20

ria

0.20

eline

0.19

olph

0.18

amos

0.18

elman

0.18

Activations Density 0.015%

mentions of advertisements or promotional content

No Comments

No Known Activations