INDEX

Explanations

phrases that express imaginative scenarios or possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

iente

-0.15

ondheim

-0.15

ropol

-0.15

æ¿

-0.15

incinn

-0.14

itzer

-0.14

 putas

-0.14

optera

-0.13

ientes

-0.13

manent

-0.13

POSITIVE LOGITS

nut

0.15

ANNEL

0.15

elic

0.14

anni

0.14

ae

0.14

amespace

0.14

ouri

0.14

ê°ĳ

0.14

eros

0.14

eric

0.14

Activations Density 0.131%

phrases that express imaginative scenarios or possibilities

No Comments

No Known Activations