INDEX

Explanations

instances of the letter 'p' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ages

-0.15

riet

-0.15

ola

-0.15

arser

-0.14

 costing

-0.14

ulses

-0.14

 Carousel

-0.14

 Trab

-0.13

sch

-0.13

Î¬Î½Ïī

-0.13

POSITIVE LOGITS

0.32

ales

0.17

ental

0.17

ivate

0.17

è¦

0.16

ison

0.16

yen

0.16

ogie

0.16

oin

0.15

early

0.15

Activations Density 0.032%

instances of the letter 'p' in various contexts

No Comments

No Known Activations