INDEX

Explanations

terms related to data protection and privacy

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

ÏĦÎ¿Î¹

-0.16

Į

-0.15

ebek

-0.15

sworth

-0.14

croft

-0.14

Embed

-0.14

ropolis

-0.14

rios

-0.13

åĪ·

-0.13

 ÑĢÐ¾ÑģÑĤ

-0.13

POSITIVE LOGITS

hei

0.16

adel

0.15

/mat

0.14

 Pins

0.14

mada

0.14

ë²Į

0.14

raÃ§

0.13

 Strateg

0.13

ycastle

0.13

Activations Density 0.002%

terms related to data protection and privacy

No Comments

No Known Activations