INDEX

Explanations

structured data related to contact and organizational information

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

oj

-0.15

abis

-0.15

wcs

-0.15

SSF

-0.14

ander

-0.14

_epsilon

-0.14

_typeof

-0.14

essenger

-0.14

çĽŁ

-0.14

ynet

-0.14

POSITIVE LOGITS

 Harley

0.14

Aur

0.14

avenport

0.14

DIY

0.14

Cab

0.14

 Trib

0.13

 tá»Ļc

0.13

Lap

0.13

adin

0.13

Activations Density 0.058%

structured data related to contact and organizational information

No Comments

No Known Activations