INDEX

Explanations

phrases that indicate actions related to management and responsibilities rather than pure narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

emey

-0.16

 Ð¾Ð±ÑĢÐ°

-0.15

llx

-0.15

bjerg

-0.14

stanov

-0.14

edback

-0.13

lsa

-0.13

ìļ

-0.13

anio

-0.13

ContextHolder

-0.13

POSITIVE LOGITS

 company

0.20

 Company

0.19

 official

0.17

 hotel

0.15

âĢ¦↵

0.15

company

0.15

 Hotel

0.14

 Ø§ÙĦØ´Ø±ÙĥØ©

0.14

 University

0.14

hotel

0.14

Activations Density 0.183%

phrases that indicate actions related to management and responsibilities rather than pure narrative

No Comments

No Known Activations