INDEX

Explanations

phrases that convey the concept of pushing boundaries or testing limits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

emouth

-0.17

æħĭ

-0.15

Ã¡cil

-0.15

gem

-0.15

ltk

-0.15

enery

-0.14

.scalablytyped

-0.14

.diag

-0.14

\grid

-0.14

ÐµÐºÑģÐ¸

-0.14

POSITIVE LOGITS

 limits

0.42

 Limits

0.38

 boundaries

0.35

limits

0.34

 limit

0.32

 bounds

0.31

Limits

0.30

 limite

0.30

 boundary

0.29

 LIMIT

0.27

Activations Density 0.072%

phrases that convey the concept of pushing boundaries or testing limits

No Comments

No Known Activations