INDEX

Explanations

variations of the abbreviation "St." related to locations or addresses

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

 Reader

-0.15

chool

-0.15

 Gros

-0.15

Mej

-0.15

agic

-0.14

iry

-0.14

 Alman

-0.14

 Acad

-0.14

erais

-0.14

 Rank

-0.14

POSITIVE LOGITS

reck

0.32

ift

0.31

amm

0.30

imm

0.29

ufen

0.29

ellung

0.27

aat

0.26

Ã¤nd

0.25

ellen

0.25

elle

0.25

Activations Density 0.008%

variations of the abbreviation "St." related to locations or addresses

No Comments

No Known Activations