INDEX

Explanations

discussions about complex relationships and societal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

wich

-0.15

oleÄį

-0.15

ucs

-0.14

à¸°

-0.14

 concrete

-0.14

_KIND

-0.14

inh

-0.14

lit

-0.13

 polished

-0.13

Lit

-0.13

POSITIVE LOGITS

 merely

0.34

 mere

0.28

 simplement

0.28

mere

0.28

 simply

0.25

 harmless

0.21

 Ð¿ÑĢÐ¾ÑģÑĤÐ¾

0.20

 Simply

0.20

åıªæĺ¯

0.19

Simply

0.19

Activations Density 0.227%

discussions about complex relationships and societal issues

No Comments

No Known Activations