INDEX

Explanations

references to television shows and their related figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 generator

-0.16

 Generator

-0.15

iefs

-0.15

auf

-0.14

loyd

-0.14

aklÄ±

-0.14

unan

-0.13

 Stud

-0.13

æ®µ

-0.13

POSITIVE LOGITS

łģ

0.16

pt

0.16

iaux

0.15

-et

0.15

avorites

0.15

Ã©mon

0.15

ascript

0.14

é³¥

0.14

rpt

0.14

ux

0.14

Activations Density 0.058%

references to television shows and their related figures

No Comments

No Known Activations