INDEX

Explanations

quantitative comparisons and measurements related to weight, water, and population statistics

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

Å¡ak

-0.15

 somehow

-0.15

 whenever

-0.14

yz

-0.14

 Ø¯ÛĮÚ¯Ø±ÛĮ

-0.14

plib

-0.14

sak

-0.14

 ÑıÐ²

-0.14

éı¡

-0.14

-0.13

POSITIVE LOGITS

 typical

0.56

 average

0.46

 Typical

0.44

typ

0.44

average

0.41

 Average

0.35

Average

0.34

åħ¸

0.31

-average

0.31

Typ

0.31

Activations Density 0.308%

quantitative comparisons and measurements related to weight, water, and population statistics

No Comments

No Known Activations