INDEX

Explanations

references to generosity and support

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

ÑĨÐµÑģ

-0.16

si

-0.15

uron

-0.15

ÐµÐ¹

-0.14

shint

-0.14

statt

-0.14

Ð¾Ð¼ÐµÐ½

-0.14

eday

-0.14

Ã©k

-0.14

te

-0.14

POSITIVE LOGITS

ones

0.16

oftware

0.15

ONES

0.14

æ¦ľ

0.14

ADVERTISEMENT

0.14

antee

0.14

ware

0.14

ously

0.14

ussia

0.13

Activations Density 0.015%

references to generosity and support

No Comments

No Known Activations