INDEX

Explanations

numerical data, particularly relating to dates and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

lis

-0.15

lap

-0.14

lap

-0.14

 Westminster

-0.14

 Fore

-0.14

 Lamar

-0.13

ring

-0.13

Lap

-0.13

POSITIVE LOGITS

 ragaz

0.16

.criteria

0.15

kiye

0.14

å®¶ä¼Ļ

0.14

.abstract

0.14

 ÐĴÐ¸ÐºÐ¸

0.14

orton

0.14

tÃ¼

0.14

æ¯Ľ

0.14

å±¬

0.13

Activations Density 0.215%

numerical data, particularly relating to dates and statistics

No Comments

No Known Activations