INDEX

Explanations

unique identifiers or symbols that signify specific data or objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 emojis

-0.13

 Zika

-0.13

-refresh

-0.13

ahlen

-0.12

 refreshed

-0.12

COVID

-0.12

 WhatsApp

-0.12

 replen

-0.12

 malware

-0.12

 ãĥ¾

-0.12

POSITIVE LOGITS

 shoulder

0.24

 neck

0.22

 waist

0.22

 forearm

0.20

 shoulders

0.20

toe

0.20

 ankle

0.20

 saddle

0.20

 bending

0.20

 knee

0.19

Activations Density 0.051%

unique identifiers or symbols that signify specific data or objects

No Comments

No Known Activations