INDEX

Explanations

terms related to algorithms and statistical analysis in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

emme

-0.16

 dressing

-0.15

åĿĬ

-0.15

foreign

-0.15

aton

-0.15

AVA

-0.14

edir

-0.14

liÄŁ

-0.14

ocab

-0.13

edm

-0.13

POSITIVE LOGITS

 Branch

0.22

 branch

0.21

 clad

0.21

Branch

0.20

 evolutionary

0.20

cl

0.20

phy

0.20

branch

0.19

 branches

0.19

 sens

0.19

Activations Density 0.233%

terms related to algorithms and statistical analysis in a scientific context

No Comments

No Known Activations