INDEX

Explanations

intensifiers that enhance the quality or degree of an attribute

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

iversit

-0.19

.getvalue

-0.19

ÐµÑĢÐ¾Ð²

-0.15

ãģĦãģĭ

-0.15

version

-0.15

nist

-0.15

era

-0.15

ital

-0.15

ivism

-0.14

votes

-0.14

POSITIVE LOGITS

yyyy

0.16

lei

0.15

 Baths

0.15

Ø¨Ø§Ø±

0.15

 Slee

0.14

(er

0.14

wen

0.14

UDO

0.13

.ly

0.13

 indeed

0.13

Activations Density 0.059%

intensifiers that enhance the quality or degree of an attribute

No Comments

No Known Activations