INDEX

Explanations

phrases starting with "what" that indicate inquiry or exploration of possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ephy

-0.15

emme

-0.15

uji

-0.14

PÅĻÃŃ

-0.14

ëĬĲ

-0.14

-0.13

.Unsupported

-0.13

uries

-0.13

Ð·Ð½Ð°Ñĩ

-0.13

ugi

-0.13

POSITIVE LOGITS

 essentially

0.18

effect

0.15

 basically

0.15

grass

0.15

 becoming

0.15

uda

0.15

 promises

0.15

 affection

0.15

stral

0.15

 fond

0.15

Activations Density 0.035%

phrases starting with "what" that indicate inquiry or exploration of possibilities

No Comments

No Known Activations