INDEX

Explanations

patterns related to legal and ethical considerations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

itos

-0.15

 diam

-0.14

.borrow

-0.14

ili

-0.14

 nÃ³

-0.14

è²ł

-0.14

 terr

-0.14

 Jewel

-0.14

 Tele

-0.14

à¤Łà¤°

-0.13

POSITIVE LOGITS

ADX

0.17

rix

0.16

ãĥĥãĥģ

0.15

erras

0.15

Ø±Ø§Ø¯

0.15

ouce

0.14

olia

0.14

enticator

0.13

.Large

0.13

Sharper

0.13

Activations Density 0.248%

patterns related to legal and ethical considerations in various contexts

No Comments

No Known Activations