INDEX

Explanations

entities and names related to organizations or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

rror

-0.16

 Ð·Ð°Ð²Ð¸

-0.15

_Tis

-0.15

à¸Ńà¸ĩà¸Īà¸²à¸ģ

-0.15

istrovstvÃŃ

-0.14

ıi

-0.14

(æ°´

-0.14

_mE

-0.14

estro

-0.14

 mÃ¡t

-0.14

POSITIVE LOGITS

orem

0.18

ayah

0.16

RIORITY

0.14

bes

0.14

ocene

0.14

pedia

0.14

visa

0.14

atin

0.13

Ð»Ð¸Ñĩ

0.13

 Duffy

0.13

Activations Density 2.070%

entities and names related to organizations or institutions

No Comments

No Known Activations