INDEX

Explanations

phrases indicating future predictions or considerations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 sometimes

-0.18

sometimes

-0.16

Sometimes

-0.16

 Sometimes

-0.15

bose

-0.14

rones

-0.14

being

-0.14

áº

-0.14

du

-0.14

ometimes

-0.14

POSITIVE LOGITS

 soon

0.28

be

0.23

 Soon

0.23

soon

0.20

 tomorrow

0.20

Soon

0.20

 shortly

0.18

 hopefully

0.17

 forthcoming

0.17

 Tomorrow

0.17

Activations Density 0.830%

phrases indicating future predictions or considerations

No Comments

No Known Activations