INDEX

Explanations

references to issues regarding limits or conditions primarily associated with numerical or status indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ãĥĭãĤ¢

-0.17

ias

-0.15

antry

-0.15

cia

-0.14

 mild

-0.14

nb

-0.14

adia

-0.14

tober

-0.14

elia

-0.14

à¸£à¸ĵ

-0.14

POSITIVE LOGITS

urm

0.19

Vit

0.16

Credentials

0.15

lich

0.15

Fcn

0.14

obuf

0.14

/Dk

0.14

spi

0.14

uess

0.14

Activations Density 0.025%

references to issues regarding limits or conditions primarily associated with numerical or status indicators

No Comments

No Known Activations