INDEX

Explanations

specific technical or scientific terms and abbreviations related to health and nutrition

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

iban

-0.17

ije

-0.16

otte

-0.16

aban

-0.15

lyph

-0.15

à¸¶à¸ģ

-0.15

nonnull

-0.15

aeda

-0.14

oci

-0.14

POSITIVE LOGITS

anitize

0.16

 uncon

0.15

iseum

0.15

.utf

0.15

 prevailing

0.14

 Team

0.14

adin

0.14

 Tight

0.14

 Fowler

0.14

Activations Density 0.093%

specific technical or scientific terms and abbreviations related to health and nutrition

No Comments

No Known Activations