INDEX

Explanations

titles and references related to literary works and their authors

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

udu

-0.17

-0.16

Teh

-0.15

oref

-0.14

Adj

-0.14

æŀ

-0.14

 simpl

-0.14

 simplified

-0.14

ijken

-0.14

POSITIVE LOGITS

 part

0.23

 among

0.20

part

0.19

 souÄįÃ¡st

0.19

 parte

0.19

 amongst

0.18

 componente

0.18

among

0.18

 component

0.17

 fourth

0.17

Activations Density 0.258%

titles and references related to literary works and their authors

No Comments

No Known Activations