INDEX

Explanations

references to time and upcoming events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

eryl

-0.17

middlewares

-0.15

echa

-0.15

midt

-0.15

-indent

-0.15

straints

-0.14

inges

-0.14

Ã¡zd

-0.14

celik

-0.14

à¥įà¤

-0.14

POSITIVE LOGITS

 less

0.20

 mere

0.19

 tomorrow

0.19

 exactly

0.18

 Less

0.18

mere

0.17

Less

0.17

wen

0.17

 thick

0.16

 months

0.16

Activations Density 0.078%

references to time and upcoming events

No Comments

No Known Activations