INDEX

Explanations

references to official entities or regulatory processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

este

-0.16

aras

-0.14

ACP

-0.14

Äįit

-0.14

edin

-0.14

eken

-0.14

eres

-0.14

 Spoon

-0.14

ernet

-0.14

iendo

-0.14

POSITIVE LOGITS

ardon

0.17

nton

0.15

ilo

0.14

ewis

0.14

iets

0.14

acre

0.14

æŁ´

0.13

à¸¢à¸§

0.13

how

0.13

Activations Density 0.263%

references to official entities or regulatory processes

No Comments

No Known Activations