INDEX

Explanations

elements related to product quality and testing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

Éµ

-0.19

kontakte

-0.16

ude

-0.15

 perse

-0.14

leon

-0.14

iane

-0.14

-0.13

onn

-0.13

oug

-0.13

Ã¨ge

-0.13

POSITIVE LOGITS

 offered

0.20

var

0.17

·»

0.15

 reck

0.15

ě

0.15

VD

0.15

raÃ§

0.14

 Boeh

0.14

var

0.14

_PARTITION

0.14

Activations Density 0.006%

elements related to product quality and testing

No Comments

No Known Activations