INDEX

Explanations

references to formal procedures or approvals in a regulatory context

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

mens

-0.17

iros

-0.17

.sessions

-0.16

ensen

-0.16

oir

-0.15

olini

-0.15

ç¨

-0.14

 dÃ¡n

-0.14

.CreateInstance

-0.14

ourke

-0.13

POSITIVE LOGITS

adol

0.16

andon

0.15

 spot

0.14

iez

0.14

 Departments

0.14

andes

0.14

IU

0.14

INY

0.13

MLE

0.13

afs

0.13

Activations Density 0.021%

references to formal procedures or approvals in a regulatory context

No Comments

No Known Activations