INDEX

Explanations

dates and time references in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Coal

-0.16

£½

-0.16

 Coalition

-0.15

 belli

-0.15

IMS

-0.14

Bro

-0.14

coal

-0.14

é¡¿

-0.13

 Coal

-0.13

tin

-0.13

POSITIVE LOGITS

ê¹Įì§Ģ

0.19

gba

0.17

ãģ¾ãģ§

0.16

 Herbert

0.16

_kses

0.15

 à¤¤à¤ķ

0.15

ole

0.15

ibold

0.15

StateException

0.15

igg

0.15

Activations Density 0.097%

dates and time references in text

No Comments

No Known Activations