INDEX

Explanations

references to the most recent updates or trends

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 pole

-0.15

uele

-0.15

if

-0.15

Ð´Ð°Ð¿

-0.14

pole

-0.14

 orig

-0.14

-0.13

POSITIVE LOGITS

/current

0.23

/latest

0.19

0.17

sik

0.16

est

0.15

ovation

0.15

ustr

0.15

maal

0.15

 Ð¾ÐºÑĢÑĥÐ¶

0.14

icks

0.14

Activations Density 0.013%

references to the most recent updates or trends

No Comments

No Known Activations