INDEX

Explanations

historical figures and events related to significant individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

–

-0.19

 whilst

-0.17

 amongst

-0.17

 famously

-0.17

-0.16

 towards

-0.15

—

-0.14

 standalone

-0.14

‘

-0.14

POSITIVE LOGITS

 Äįe

0.17

olid

0.15

ãĤ¤ãĥī

0.14

lek

0.14

 pylint

0.14

neau

0.14

Aura

0.14

ylko

0.14

ÑĢÐ°ÑĤÐ½Ð¾

0.13

/owl

0.13

Activations Density 0.149%

historical figures and events related to significant individuals

No Comments

No Known Activations