INDEX

Explanations

instances of negative or ridiculing language

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

æĹıèĩªæ²»

-0.17

mdb

-0.16

abwe

-0.15

nero

-0.15

iros

-0.15

eren

-0.15

_typeof

-0.14

à¸ĺà¸£à¸£à¸¡

-0.14

Ã¡genes

-0.14

ÑĩÐ¸ÑģÐ»

-0.14

POSITIVE LOGITS

MO

0.19

0.17

Mo

0.16

mo

0.16

MO

0.15

 Moore

0.15

 Func

0.15

 Holmes

0.15

Activations Density 0.031%

instances of negative or ridiculing language

No Comments

No Known Activations