INDEX

Explanations

references to mathematical elements and frameworks in programming

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

otts

-0.16

 compliment

-0.14

mont

-0.14

Ð°ÑĢÑĩ

-0.14

elson

-0.14

yll

-0.13

aki

-0.13

å±¥

-0.13

ARGV

-0.13

nemonic

-0.13

POSITIVE LOGITS

Math

0.23

 Math

0.23

Te

0.22

jax

0.22

TeX

0.21

=Math

0.20

.Math

0.19

/Math

0.19

 math

0.18

tex

0.17

Activations Density 0.012%

references to mathematical elements and frameworks in programming

No Known Activations