INDEX

Explanations

key phrases and outcomes related to results and their significance

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

eways

-0.16

prung

-0.16

uri

-0.16

ÌĤ

-0.14

antu

-0.14

 gross

-0.14

plus

-0.14

 Siri

-0.14

ÑĢ

-0.14

POSITIVE LOGITS

vatel

0.17

Ã¶s

0.16

GameManager

0.15

eliness

0.15

lays

0.15

.operations

0.15

éģĶ

0.14

commended

0.14

è¾¾

0.14

icias

0.14

Activations Density 0.361%

key phrases and outcomes related to results and their significance

No Comments

No Known Activations