INDEX

Explanations

the word "by" in various contexts

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

 actionTypes

-0.16

ova

-0.15

ç«¯

-0.15

 ActionTypes

-0.15

fram

-0.15

urs

-0.14

store

-0.13

aller

-0.13

Î½Î±Î½

-0.13

\Dependency

-0.13

POSITIVE LOGITS

 default

0.29

 proxy

0.23

-default

0.23

 accident

0.22

-proxy

0.21

 necessity

0.20

default

0.20

 definition

0.20

 Default

0.19

 pure

0.19

Activations Density 0.055%

the word "by" in various contexts

No Comments

No Known Activations