INDEX

Explanations

citations and references in academic writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

anse

-0.15

 oran

-0.15

 crop

-0.15

ume

-0.15

iores

-0.14

 Cloth

-0.14

smo

-0.14

osen

-0.14

azes

-0.14

 caps

-0.14

POSITIVE LOGITS

ateurs

0.17

ateur

0.15

grab

0.14

NECTION

0.14

voz

0.14

ulators

0.14

 ÄĳoÃłn

0.14

adena

0.13

xampp

0.13

scal

0.13

Activations Density 0.002%

citations and references in academic writing

No Comments

No Known Activations