INDEX

Explanations

the proper nouns, particularly names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

tual

-0.18

upal

-0.17

Ñĥ

-0.17

ĶåĽŀ

-0.16

bower

-0.16

Ã±a

-0.16

erton

-0.15

es

-0.15

LOW

-0.15

uro

-0.15

POSITIVE LOGITS

ymous

0.24

avirus

0.21

imbus

0.20

ically

0.20

ettes

0.19

che

0.18

ise

0.17

script

0.17

ics

0.17

ENTIAL

0.17

Activations Density 0.158%

the proper nouns, particularly names and locations

No Comments

No Known Activations