INDEX

Explanations

instances of encouragement and motivation 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 @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

achten

-0.15

ound

-0.15

cket

-0.15

enton

-0.15

orc

-0.14

_initialize

-0.14

ake

-0.13

aroo

-0.13

atars

-0.13

ARED

-0.13

POSITIVE LOGITS

 towards

0.21

 toward

0.20

 encouraged

0.20

oward

0.18

 ambient

0.18

emb

0.17

to

0.16

pson

0.16

 encourage

0.16

 Confidence

0.16

Activations Density 0.097%

instances of encouragement and motivation in various contexts

No Comments

No Known Activations