INDEX

Explanations

references to structured data relationships and components within a system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

TEE

-0.15

ç«Ł

-0.15

SAFE

-0.15

ori

-0.14

ipi

-0.14

ednou

-0.14

nya

-0.14

jos

-0.14

ius

-0.14

æ³ķ

-0.14

POSITIVE LOGITS

ataka

0.15

æķ£

0.15

 Interr

0.14

Mounted

0.14

 POSSIBILITY

0.14

Ã¡u

0.14

plode

0.13

ÛĮØ²ÛĮ

0.13

 ÐĴÐ¸ÐºÐ¸

0.13

é³¥

0.13

Activations Density 0.027%

references to structured data relationships and components within a system

No Comments

No Known Activations