INDEX

Explanations

occurrences of the word "the" and related articles or nouns in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ç§

-0.16

ModifiedDate

-0.15

pressive

-0.15

mont

-0.14

ylko

-0.13

rod

-0.13

vor

-0.13

upertino

-0.13

afd

-0.13

 meantime

-0.13

POSITIVE LOGITS

 ones

0.23

ones

0.14

PIO

0.14

tpl

0.13

mine

0.13

egrator

0.13

 meiden

0.13

mÃ¼r

0.13

nila

0.13

ForResult

0.13

Activations Density 0.131%

occurrences of the word "the" and related articles or nouns in a document

No Comments

No Known Activations