INDEX

Explanations

text related to programming functions and data structures

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

ublik

-0.14

dsl

-0.14

alah

-0.14

 UNIVERS

-0.14

slick

-0.14

ProcessEvent

-0.14

plib

-0.13

vaÅ¾

-0.13

ye

-0.13

tooltip

-0.13

POSITIVE LOGITS

istÃ©

0.18

Skin

0.15

vido

0.15

ëį°ìĿ´íĬ¸

0.15

 Skin

0.15

ppard

0.14

è¸

0.14

åĢ

0.14

WR

0.14

MCS

0.14

Activations Density 0.008%

text related to programming functions and data structures

No Comments

No Known Activations