INDEX

Explanations

details about accommodations and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

FFFFFFFF

-0.14

agent

-0.13

ateria

-0.13

çµ¶

-0.13

icy

-0.13

ader

-0.13

 Lust

-0.13

     č↵

-0.12

Dies

-0.12

Ð¾ÑıÐ½

-0.12

POSITIVE LOGITS

 fold

0.25

fut

0.24

 pull

0.24

 twin

0.23

 queen

0.23

Fut

0.22

 Twin

0.21

pull

0.21

 Pull

0.21

 Queen

0.20

Activations Density 0.025%

details about accommodations and their features

No Comments

No Known Activations