INDEX

Explanations

numerical representations or references to specific episodes or seasons in a series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

isci

-0.17

-0.16

heimer

-0.16

conomy

-0.16

atan

-0.15

Æ°u

-0.15

ermann

-0.15

åĴ

-0.14

 handjob

-0.14

yr

-0.14

POSITIVE LOGITS

-fontawesome

0.15

DownList

0.15

kus

0.15

NavigationView

0.15

ÑĨÐµÐ¿

0.14

EOF

0.14

Deployment

0.14

 SÃ¼r

0.14

HomeAsUpEnabled

0.14

 WaitFor

0.14

Activations Density 0.005%

numerical representations or references to specific episodes or seasons in a series

No Comments

No Known Activations