INDEX

Explanations

key concepts and structural elements related to solutions and answers within a discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ebi

-0.15

lvl

-0.15

itz

-0.15

áº¡nh

-0.15

Äħd

-0.14

ideas

-0.13

Î³Î¿

-0.13

oser

-0.13

udas

-0.13

 ÏĦÎ¬

-0.13

POSITIVE LOGITS

 equation

0.54

 Equation

0.37

 puzzle

0.35

mix

0.33

 equations

0.32

 picture

0.31

 arsenal

0.30

 fabric

0.27

 package

0.27

 recipe

0.26

Activations Density 0.339%

key concepts and structural elements related to solutions and answers within a discussion

No Comments

No Known Activations