INDEX

Explanations

patterns and structures in programming syntax, particularly focusing on functions and variable manipulations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

brig

-0.17

alendar

-0.14

olumn

-0.14

oze

-0.13

oth

-0.13

OLOR

-0.13

entai

-0.13

.bp

-0.13

 tslint

-0.13

fo

-0.13

POSITIVE LOGITS

Rav

0.15

orta

0.15

asi

0.15

 Evel

0.14

à¤Łà¤°

0.14

Col

0.13

rita

0.13

olla

0.13

zend

0.13

 Horton

0.13

Activations Density 0.994%

patterns and structures in programming syntax, particularly focusing on functions and variable manipulations

No Comments

No Known Activations