INDEX

Explanations

the preposition "by" and its variations, indicating authorship or attribution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

isci

-0.18

cliffe

-0.17

ego

-0.15

mage

-0.15

 Merrill

-0.14

è²¼

-0.14

fort

-0.14

oa

-0.14

wald

-0.14

ese

-0.14

POSITIVE LOGITS

 Lesbian

0.16

owell

0.15

Ã³z

0.15

oder

0.15

Ð´Ð¸

0.14

kola

0.14

 rais

0.14

dek

0.14

.bukkit

0.14

 odak

0.14

Activations Density 0.005%

the preposition "by" and its variations, indicating authorship or attribution

No Comments

No Known Activations