INDEX

Explanations

modals that express capability or possibility

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.16

-0.15

oker

-0.15

env

-0.15

las

-0.14

zes

-0.14

ngen

-0.14

 Magnum

-0.14

gam

-0.14

es

-0.14

POSITIVE LOGITS

!=(

0.17

repid

0.16

EObject

0.15

ìĸ

0.15

/license

0.14

.PropTypes

0.14

ÐºÐ»Ð°Ð´

0.14

__$

0.14

èħ

0.14

ORAGE

0.14

Activations Density 0.066%

modals that express capability or possibility

No Comments

No Known Activations

modals that express capability or possibility

No Comments

No Known Activations