INDEX

Explanations

instances of the word "pres" and its variations, which relate to authority or administration

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

iper

-0.18

acz

-0.16

ÃŃsticas

-0.15

richt

-0.15

)prepare

-0.14

isper

-0.14

spir

-0.14

 Wolfe

-0.14

chine

-0.14

 Mane

-0.14

POSITIVE LOGITS

 Pres

0.25

 pres

0.22

Pres

0.20

pres

0.20

.pres

0.18

-pres

0.17

umably

0.16

_pres

0.16

byterian

0.16

bÃŃ

0.15

Activations Density 0.024%

instances of the word "pres" and its variations, which relate to authority or administration

No Comments

No Known Activations