INDEX

Explanations

fragments of URLs or paths in code or technical documentation

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

_startup

-0.16

ught

-0.15

ynet

-0.14

emens

-0.14

lic

-0.14

jur

-0.14

atz

-0.14

aciente

-0.14

ertz

-0.14

POSITIVE LOGITS

ries

0.18

arin

0.16

á»§

0.15

lection

0.15

drawing

0.14

Ere

0.14

Woj

0.14

/includes

0.14

 rang

0.14

macros

0.14

Activations Density 0.004%

fragments of URLs or paths in code or technical documentation

No Comments

No Known Activations