INDEX

Explanations

instances of the German word "Einsatz," indicating a focus on involvement or utilization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

åĩºåĵģ

-0.16

peq

-0.15

ksen

-0.15

ash

-0.14

CDATA

-0.14

oxic

-0.14

orang

-0.14

_OVERRIDE

-0.14

orgh

-0.13

ãĤĿ

-0.13

POSITIVE LOGITS

0.17

idency

0.16

cul

0.15

sted

0.15

sik

0.15

esture

0.15

sand

0.15

amerate

0.14

handleSubmit

0.14

 vice

0.14

Activations Density 0.004%

instances of the German word "Einsatz," indicating a focus on involvement or utilization

No Comments

No Known Activations