INDEX

Explanations

references to magazines and periodicals

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

ungeons

-0.16

ÑģÑı

-0.16

anks

-0.15

uggage

-0.15

orage

-0.15

ittel

-0.15

abs

-0.15

leigh

-0.15

alk

-0.14

udi

-0.14

POSITIVE LOGITS

azines

0.24

azine

0.20

-format

0.20

-style

0.19

esium

0.16

-like

0.16

/new

0.16

ëħĲ

0.16

gesi

0.16

ging

0.15

Activations Density 0.021%

references to magazines and periodicals

No Comments

No Known Activations