INDEX

Explanations

prepositions indicating containment or placement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Tomas

-0.14

 Ð¿ÑĢÐ¸Ð¼

-0.14

éĢ¸

-0.14

iw

-0.14

ampling

-0.14

legg

-0.14

è£ķ

-0.14

QL

-0.14

Calibri

-0.13

//{{

-0.13

POSITIVE LOGITS

lay

0.18

uo

0.17

ANNER

0.17

itta

0.15

ÎŃÏģÎ³

0.15

ocab

0.15

 situ

0.15

estic

0.14

ÏĦÎ¹

0.14

Ð»Ð°Ð³Ð°

0.14

Activations Density 0.143%

prepositions indicating containment or placement

No Comments

No Known Activations