INDEX

Explanations

mathematical symbols and notations used in equations and formulas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

inery

-0.16

onis

-0.16

Ã«

-0.15

agua

-0.15

ÐµÐ½Ñĭ

-0.14

etes

-0.14

oningen

-0.13

Opp

-0.13

ames

-0.13

keterangan

-0.13

POSITIVE LOGITS

.generated

0.17

 ellipt

0.16

ë²Ī

0.13

.divide

0.13

 Inventory

0.13

ãĤ¤ãĥĪ

0.13

 Andres

0.13

Ðĭ

0.13

aurants

0.12

_Internal

0.12

Activations Density 0.264%

mathematical symbols and notations used in equations and formulas

No Comments

No Known Activations