INDEX

Explanations

actions and concepts related to learning, development, and individual initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ized

-0.17

ly

-0.17

culus

-0.16

uously

-0.16

agonal

-0.16

uish

-0.16

ordin

-0.15

istically

-0.15

atically

-0.15

osate

-0.15

POSITIVE LOGITS

ings

0.45

able

0.36

ÂŃing

0.36

INGS

0.29

ability

0.26

eds

0.25

ables

0.24

ABLE

0.23

ableObject

0.21

inator

0.20

Activations Density 0.953%

actions and concepts related to learning, development, and individual initiatives

No Comments

No Known Activations