INDEX

Explanations

phrases indicating intention or future actions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

abyrin

-0.16

oppable

-0.14

ongs

-0.14

amas

-0.14

bject

-0.14

lds

-0.14

 ServiceException

-0.14

]âĢı

-0.14

Ø§Ø¡

-0.14

_ut

-0.14

POSITIVE LOGITS

 tele

0.17

aroo

0.14

@_

0.14

ÑĢÐ°Ð²Ð°

0.14

tele

0.14

iage

0.14

 Telegram

0.14

 Sche

0.14

owo

0.14

 ÙĦÙĤ

0.13

Activations Density 0.061%

phrases indicating intention or future actions

No Comments

No Known Activations