INDEX

Explanations

references to the processes of reading and reviewing documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ATUS

-0.17

ijken

-0.15

pod

-0.15

odyn

-0.14

adem

-0.14

casts

-0.14

 podcasts

-0.14

 enqu

-0.14

beeld

-0.14

ØªØ²

-0.14

POSITIVE LOGITS

 torn

0.29

 stap

0.27

 tore

0.26

 penc

0.25

 circ

0.25

 tear

0.24

 scri

0.24

 staple

0.24

 Stap

0.24

 phot

0.23

Activations Density 0.393%

references to the processes of reading and reviewing documents

No Comments

No Known Activations