INDEX

Explanations

references to observations and assertions made by individuals or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

å±ŀäºİ

-0.14

imson

-0.13

/if

-0.13

Ð¾Ð¿Ð¸Ñģ

-0.13

çľŁçļĦ

-0.12

reck

-0.12

æĪĸèĢħ

-0.12

 Ø¨ÙĨØ§

-0.12

ÙģÙĩ

-0.12

ÛĮØªÛĮ

-0.12

POSITIVE LOGITS

how

0.33

 similarities

0.30

 that

0.27

 parallels

0.25

 examples

0.24

how

0.23

 instances

0.22

 several

0.22

 differences

0.22

 again

0.21

Activations Density 0.108%

references to observations and assertions made by individuals or organizations

No Comments

No Known Activations