INDEX

Explanations

quantifiers that emphasize abundance or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

pen

-0.16

nist

-0.15

irie

-0.15

umn

-0.14

swer

-0.14

istrovstvÃŃ

-0.14

umu

-0.14

gio

-0.14

halb

-0.14

istical

-0.13

POSITIVE LOGITS

/all

0.22

-many

0.21

ToMany

0.21

-times

0.20

 times

0.19

 different

0.18

fold

0.18

of

0.16

ãĢħ

0.16

 sayÄ±da

0.16

Activations Density 0.077%

quantifiers that emphasize abundance or quantities

No Comments

No Known Activations