INDEX

Explanations

references to gaps or disparities in various contexts, particularly those relating to inequality or balance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

resco

-0.18

tte

-0.16

hq

-0.15

orias

-0.14

enschaft

-0.14

bÃŃ

-0.14

aque

-0.14

er

-0.14

à¹Ģà¸Ħ

-0.14

vale

-0.14

POSITIVE LOGITS

 between

0.25

 filler

0.24

 filled

0.23

wid

0.23

-gap

0.22

 closing

0.22

 opening

0.22

Closing

0.22

fill

0.22

 brid

0.22

Activations Density 0.027%

references to gaps or disparities in various contexts, particularly those relating to inequality or balance

No Comments

No Known Activations