INDEX

Explanations

words related to hierarchy and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Bilg

-0.17

amed

-0.15

Ã¥n

-0.15

Hat

-0.14

ainment

-0.14

Gre

-0.14

inz

-0.14

 minded

-0.13

inh

-0.13

ifo

-0.13

POSITIVE LOGITS

çı

0.18

annels

0.14

kelas

0.13

((__

0.13

Ĥ¬

0.13

ucs

0.13

.commons

0.13

Î³ÎºÎ±

0.13

elop

0.13

laz

0.13

Activations Density 0.122%

words related to hierarchy and governance

No Comments

No Known Activations