INDEX

Explanations

instances of the word "Sem" and its variations, indicating a focus on semantic or seminary-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

iets

-0.21

anela

-0.19

omer

-0.16

Ð¾Ð¼ÐµÑĢ

-0.16

umlu

-0.15

typeorm

-0.15

atitude

-0.15

pga

-0.15

inand

-0.15

bette

-0.15

POSITIVE LOGITS

inary

0.26

antics

0.22

olina

0.22

antically

0.22

esters

0.21

iotics

0.20

iotic

0.19

inars

0.18

(sem

0.18

sem

0.18

Activations Density 0.013%

instances of the word "Sem" and its variations, indicating a focus on semantic or seminary-related content

No Comments

No Known Activations