INDEX

Explanations

numerical data and references related to existing datasets or articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÑĢÐ¸Ð·

-0.15

/navigation

-0.14

ucher

-0.14

CID

-0.14

iales

-0.13

 Hawth

-0.13

idon

-0.13

lim

-0.13

bett

-0.13

 RectTransform

-0.13

POSITIVE LOGITS

ients

0.17

 Trib

0.14

enos

0.14

ÑĢÐ°ÑĤÐ½Ð¾

0.14

 Wire

0.14

ìłĪ

0.14

ui

0.14

itions

0.14

iculos

0.13

pected

0.13

Activations Density 0.052%

numerical data and references related to existing datasets or articles

No Comments

No Known Activations