INDEX

Explanations

time-related symbols and indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ÙĥØ§ÙĦ

-0.18

iphy

-0.15

Cow

-0.15

ace

-0.15

cav

-0.14

illian

-0.14

wie

-0.14

oge

-0.14

POSITIVE LOGITS

0.21

 ÛĮÙĪØªÛĮ

0.18

0.17

0.16

UCT

0.16

0.15

bras

0.15

Activations Density 0.008%

time-related symbols and indicators

No Comments

No Known Activations