INDEX

Explanations

questions and hints related to literary or analytical challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Ukra

-0.15

esome

-0.14

vn

-0.14

 authDomain

-0.14

thro

-0.14

imitives

-0.14

anlÄ±

-0.14

dma

-0.14

 Aspect

-0.14

pot

-0.13

POSITIVE LOGITS

hint

0.28

 guess

0.27

 guesses

0.27

Hint

0.26

 Hint

0.23

 guessed

0.22

guess

0.21

Spo

0.21

 Guess

0.21

 hint

0.19

Activations Density 0.156%

questions and hints related to literary or analytical challenges

No Comments

No Known Activations