INDEX

Explanations

terms related to education and educational activities

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

ances

-0.16

ãĥ¼ãĥ³

-0.15

aturas

-0.15

ANCES

-0.15

 embr

-0.15

ellig

-0.15

 homeland

-0.14

ily

-0.14

ELY

-0.14

 Ð¿Ð¾Ð²ÐµÑĢ

-0.14

POSITIVE LOGITS

ational

0.26

ationally

0.22

ATIONAL

0.21

maz

0.19

acional

0.19

uation

0.18

ators

0.17

uela

0.15

zion

0.15

ì¼ĢìĿ´

0.15

Activations Density 0.010%

terms related to education and educational activities

No Comments

No Known Activations