INDEX

Explanations

references to personal pronouns and the expression of individual desires or intentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

should

-0.15

itr

-0.14

 should

-0.14

WE

-0.14

issing

-0.14

ä¹ī

-0.14

 ought

-0.14

æķı

-0.13

 Telerik

-0.13

anz

-0.13

POSITIVE LOGITS

Ã©al

0.16

 Baths

0.16

ohon

0.15

allet

0.15

ror

0.15

rava

0.15

è§īå¾Ĺ

0.14

è¦º

0.14

ÐµÐ»Ð¾

0.14

aign

0.14

Activations Density 0.276%

references to personal pronouns and the expression of individual desires or intentions

No Comments

No Known Activations