INDEX

Explanations

instances of the word "für" and its variations, indicating a focus on purpose or function in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Î·ÏĤ

-0.18

 himself

-0.17

 thems

-0.17

 themselves

-0.16

 however

-0.15

emap

-0.15

ertest

-0.14

 swingerclub

-0.14

icontrol

-0.14

our

-0.14

POSITIVE LOGITS

den

0.46

die

0.44

das

0.43

 einen

0.37

 eine

0.32

 diesen

0.32

 diese

0.30

 seine

0.29

 seinen

0.28

 ihren

0.28

Activations Density 0.020%

instances of the word "für" and its variations, indicating a focus on purpose or function in the text

No Comments

No Known Activations