INDEX

Explanations

terms related to regulations and qualifications in various contexts, such as employment and academic settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

.YesNo

-0.17

ÑģÑİ

-0.14

ropol

-0.13

ÅĽÄĩ

-0.13

 realise

-0.13

 Sala

-0.13

onte

-0.13

 because

-0.13

çĶļèĩ³

-0.13

ondon

-0.13

POSITIVE LOGITS

ħ

0.15

asel

0.14

abay

0.14

yer

0.14

CSA

0.13

zed

0.13

ANT

0.13

abol

0.13

abc

0.13

_ped

0.13

Activations Density 0.122%

terms related to regulations and qualifications in various contexts, such as employment and academic settings

No Comments

No Known Activations