INDEX

Explanations

mathematical notations and variables used in formulae or proofs

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

 Revenge

-0.15

urry

-0.15

HI

-0.14

ole

-0.14

 geometric

-0.14

oser

-0.14

emme

-0.14

eth

-0.13

dale

-0.13

chu

-0.13

POSITIVE LOGITS

âĹİ

0.17

adows

0.16

encion

0.15

Î¼Î¹Ïĥ

0.15

BOOLE

0.15

elsing

0.15

.abstract

0.14

Ð½Ð¾ÑĪ

0.14

Å¡li

0.14

ondo

0.13

Activations Density 0.007%

mathematical notations and variables used in formulae or proofs

No Comments

No Known Activations