INDEX

Explanations

mathematical terms and notations associated with theoretical frameworks and analysis

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

-0.14

 Stanton

-0.14

ame

-0.14

opt

-0.13

beck

-0.13

.quality

-0.13

-Sah

-0.13

POSITIVE LOGITS

svp

0.15

Å¡ak

0.15

à¥Ģà¤¦

0.15

/epl

0.14

onto

0.14

icone

0.14

Åº

0.14

 pole

0.14

Ø¨ÙĪØ§Ø³Ø·Ø©

0.14

essler

0.13

Activations Density 0.157%

mathematical terms and notations associated with theoretical frameworks and analysis

No Comments

No Known Activations