INDEX

Explanations

instances of positive feedback about a facility or service

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

mlink

-0.16

ONUS

-0.15

.'&

-0.14

ãĤ©

-0.14

zeit

-0.14

ÐµÑģÑĮ

-0.13

æŃ¡

-0.13

eniable

-0.13

ãĥ³ãĥĨ

-0.13

otti

-0.13

POSITIVE LOGITS

Pros

0.23

very

0.23

 Pros

0.23

abs

0.22

Very

0.21

 pros

0.21

 Very

0.21

 very

0.20

Cons

0.18

 decent

0.18

Activations Density 0.066%

instances of positive feedback about a facility or service

No Comments

No Known Activations

instances of positive feedback about a facility or service

No Comments

No Known Activations