INDEX

Explanations

references to relationships and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ancock

-0.15

Ð¶Ð´

-0.15

uids

-0.14

)((((

-0.14

 éĥ

-0.14

unc

-0.14

ansom

-0.14

]âĢı

-0.14

avir

-0.14

uid

-0.14

POSITIVE LOGITS

QualifiedName

0.14

 brunch

0.14

ĩ

0.14

oloji

0.13

Sha

0.13

NOP

0.13

Ð´ÑĢÐ¾Ð¼

0.13

uzzy

0.13

bow

0.13

 Walker

0.13

Activations Density 0.271%

references to relationships and interactions

No Comments

No Known Activations