INDEX

Explanations

instances of the word "let" and its variations, often in contexts implying allowance or permission

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

.Slf

-0.16

ssp

-0.16

veau

-0.15

yb

-0.15

rien

-0.15

aiser

-0.14

okt

-0.14

olland

-0.14

ÐµÐ²ÐµÑĢ

-0.14

=__

-0.14

POSITIVE LOGITS

tings

0.19

ting

0.17

chas

0.16

erea

0.16

TING

0.15

ted

0.15

us

0.15

tres

0.15

GO

0.15

Activations Density 0.049%

instances of the word "let" and its variations, often in contexts implying allowance or permission

No Comments

No Known Activations