INDEX

Explanations

personal opinions and preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Apostle

-0.16

wart

-0.16

rawer

-0.15

 Fitz

-0.15

ayo

-0.15

.getClient

-0.14

esz

-0.14

 ÑģÑħ

-0.14

irk

-0.14

ulling

-0.14

POSITIVE LOGITS

Personally

0.16

asm

0.15

asc

0.14

 Personally

0.14

ase

0.13

EE

0.13

ress

0.13

 taste

0.13

 personally

0.13

ipc

0.13

Activations Density 0.044%

personal opinions and preferences

No Comments

No Known Activations