INDEX

Explanations

instances of the root "bi" or related variations, indicating a focus on "biography" or "biographical" content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ossa

-0.15

man

-0.15

Zah

-0.15

pet

-0.15

 ngon

-0.15

ment

-0.15

ãĥĥãĤ«ãĥ¼

-0.14

ooky

-0.14

onya

-0.14

 ç²¾

-0.14

POSITIVE LOGITS

bi

0.22

Bi

0.22

Bi

0.19

ylland

0.15

otechnology

0.15

.bi

0.15

imap

0.15

_bi

0.15

-direction

0.15

LOS

0.15

Activations Density 0.010%

instances of the root "bi" or related variations, indicating a focus on "biography" or "biographical" content

No Comments

No Known Activations