INDEX

Explanations

phrases indicating expertise, qualifications, and current knowledge in specific fields

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

hcp

-0.14

à¸¢à¸Ļ

-0.14

ogo

-0.14

Uvs

-0.14

|wx

-0.14

æĹıèĩªæ²»

-0.14

ØªÙĥ

-0.14

atten

-0.13

iler

-0.13

fter

-0.13

POSITIVE LOGITS

 latest

0.70

 current

0.62

latest

0.61

æľĢæĸ°

0.59

Latest

0.56

 Latest

0.54

up

0.54

 newest

0.52

current

0.50

_latest

0.49

Activations Density 0.207%

phrases indicating expertise, qualifications, and current knowledge in specific fields

No Comments

No Known Activations