INDEX

Explanations

questions and discussions relating to personal academic experiences and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

_PB

-0.16

erville

-0.14

PD

-0.14

BLL

-0.14

apter

-0.14

ondon

-0.14

 values

-0.14

 undef

-0.14

 facts

-0.14

ogen

-0.13

POSITIVE LOGITS

 University

0.36

University

0.34

 UNIVERSITY

0.32

 Ø¬Ø§ÙħØ¹Ø©

0.28

Loy

0.28

 Universidad

0.28

 Univ

0.28

UT

0.27

 Duke

0.26

UV

0.26

Activations Density 0.804%

questions and discussions relating to personal academic experiences and processes

No Comments

No Known Activations