INDEX

Explanations

negative sentiments and phrases related to boredom or monotony

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

eck

-0.14

ÑģÑĤÑİ

-0.14

osto

-0.14

omez

-0.14

Ã²n

-0.14

rio

-0.14

(&$

-0.14

onto

-0.14

oulder

-0.13

ÃŃo

-0.13

POSITIVE LOGITS

 diff

0.15

 relent

0.14

 dint

0.14

gol

0.14

immel

0.14

èµĦ

0.13

istrovstvÃŃ

0.13

 Goldman

0.13

tsky

0.13

lich

0.13

Activations Density 0.271%

negative sentiments and phrases related to boredom or monotony

No Comments

No Known Activations