INDEX

Explanations

structured programming concepts related to class and object definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

zew

-0.15

 reserved

-0.15

dem

-0.14

parator

-0.14

hur

-0.14

reste

-0.14

-use

-0.14

kin

-0.14

 Roman

-0.13

SC

-0.13

POSITIVE LOGITS

HITE

0.19

à¹ģà¸Ļ

0.16

iqueta

0.16

Ð¾ÑĢÐ¾Ð¶

0.15

ATK

0.15

ÑĤÐµÑĢÐ½

0.14

templ

0.14

phins

0.14

 underlying

0.14

Î¹Î±Î½

0.13

Activations Density 0.053%

structured programming concepts related to class and object definitions

No Comments

No Known Activations