INDEX

Explanations

references to programming languages and associated frameworks or libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

otre

-0.15

venues

-0.15

lays

-0.14

à¹Īà¸ĩà¸Ĥ

-0.14

 Rupert

-0.14

lopen

-0.14

Vu

-0.14

iva

-0.14

 Violet

-0.14

 Mellon

-0.14

POSITIVE LOGITS

isch

0.18

vement

0.16

aland

0.14

 Clipboard

0.14

uf

0.14

viso

0.13

 ListItem

0.13

à¸²à¸¢à¸Ļ

0.13

ãĥıãĤ¤

0.13

asan

0.13

Activations Density 0.050%

references to programming languages and associated frameworks or libraries

No Comments

No Known Activations