INDEX

Explanations

phrases related to the act of applying concepts or actions 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

imei

-0.17

ksen

-0.16

asaki

-0.15

 pháº£i

-0.15

anke

-0.15

ColumnInfo

-0.14

aised

-0.14

_EXPRESSION

-0.14

elper

-0.14

stri

-0.14

POSITIVE LOGITS

çħ§

0.16

gene

0.15

 applied

0.15

ertura

0.15

ãĤĴãģĭ

0.14

chain

0.14

ERSIST

0.14

unto

0.14

llum

0.14

ivi

0.13

Activations Density 0.048%

phrases related to the act of applying concepts or actions in various contexts

No Comments

No Known Activations