INDEX

Explanations

programming-related terms and concepts within code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 updateTime

-0.17

ounce

-0.16

ounces

-0.15

 Clem

-0.13

timeout

-0.13

 quadr

-0.13

ï½¡

-0.13

è¸

-0.13

 timings

-0.13

_TIMEOUT

-0.13

POSITIVE LOGITS

 yesterday

0.27

 date

0.26

 today

0.25

 Yesterday

0.24

today

0.24

date

0.23

 dates

0.22

Yesterday

0.22

 DATE

0.22

esterday

0.21

Activations Density 0.130%

programming-related terms and concepts within code snippets

No Comments

No Known Activations