INDEX

Explanations

references to numerical data or sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

obot

-0.14

inho

-0.14

oster

-0.14

aurus

-0.14

cha

-0.13

Ã¢n

-0.13

rag

-0.13

itler

-0.13

adows

-0.13

ACS

-0.13

POSITIVE LOGITS

zon

0.17

Ð·Ð½

0.15

tpl

0.15

ulti

0.14

zion

0.14

Ã©p

0.13

ì¢ħ

0.13

 Ð·Ð°Ð¿Ð°Ñģ

0.13

ikt

0.13

ulin

0.13

Activations Density 0.014%

references to numerical data or sequences

No Comments

No Known Activations