INDEX

Explanations

references to locations or residences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

nett

-0.18

uez

-0.17

 Merc

-0.16

engu

-0.15

sov

-0.15

uss

-0.15

hone

-0.14

 Permanent

-0.14

 style

-0.14

odule

-0.14

POSITIVE LOGITS

 rezerv

0.18

_ASM

0.16

Ð°Ð¹ÑĤ

0.15

Hra

0.15

Ø²Ø´

0.15

 reserva

0.15

.undefined

0.15

ideshow

0.15

Unchecked

0.15

atÃ¶r

0.14

Activations Density 0.001%

references to locations or residences

No Comments

No Known Activations