INDEX

Explanations

phrases emphasizing the concept of tightness or close relationships

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

apore

-0.15

Ð¼ÐµÐ¶

-0.14

pNet

-0.14

Facade

-0.14

ipple

-0.14

uant

-0.14

 Interr

-0.14

OrFail

-0.14

è´¹

-0.13

pong

-0.13

POSITIVE LOGITS

ifecycle

0.19

 tight

0.19

est

0.18

ness

0.18

tight

0.17

 tighter

0.16

ened

0.16

/loose

0.15

/person

0.15

NESS

0.15

Activations Density 0.017%

phrases emphasizing the concept of tightness or close relationships

No Comments

No Known Activations