INDEX

Explanations

references to lessons and learning experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

æĬ±

-0.20

ters

-0.17

gw

-0.15

ustos

-0.15

ted

-0.14

ushed

-0.14

leston

-0.14

geist

-0.14

way

-0.14

POSITIVE LOGITS

0.21

naire

0.20

/Instruction

0.19

 Learned

0.19

alem

0.17

.googlecode

0.16

æĿĲ

0.16

oldur

0.15

ÑĢÑı

0.15

lijke

0.15

Activations Density 0.018%

references to lessons and learning experiences

No Comments

No Known Activations