INDEX

Explanations

names or references to individuals, particularly those with "Tina" or "Nina" in them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

¤ĳ

-0.16

Ã¡te

-0.16

Ø§Ø²Ùħ

-0.16

Ã½v

-0.15

anooga

-0.15

Ã¼lÃ¼

-0.15

wahl

-0.15

acyj

-0.14

.metamodel

-0.14

ttp

-0.14

POSITIVE LOGITS

0.20

uer

0.19

amate

0.17

emez

0.15

elli

0.15

les

0.15

Ø¯Ø§Ø±ÛĮ

0.15

is

0.15

res

0.14

 stip

0.14

Activations Density 0.017%

names or references to individuals, particularly those with "Tina" or "Nina" in them

No Comments

No Known Activations