INDEX

Explanations

references to specific films, particularly sequels and adaptations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ãĥ¼ãĥį

-0.16

 æģ

-0.15

.snap

-0.15

hod

-0.15

ardon

-0.15

bons

-0.14

ÐµÐ»Ðµ

-0.14

 rings

-0.14

ØªØ²

-0.14

-ring

-0.14

POSITIVE LOGITS

 Blade

0.35

 Deck

0.34

 blade

0.30

Deck

0.29

blade

0.26

 Harrison

0.25

 blades

0.23

Joi

0.22

 replic

0.22

 deck

0.22

Activations Density 0.002%

references to specific films, particularly sequels and adaptations

No Comments

No Known Activations