INDEX

Explanations

structured data fields related to program descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.14

engu

-0.14

ahun

-0.14

Ø±ÙĬÙĥÙĬ

-0.13

sten

-0.13

UCT

-0.13

leston

-0.13

ãĤ¹ãĤ¿

-0.13

hyp

-0.13

Ø§Ø·

-0.13

POSITIVE LOGITS

ipel

0.16

angan

0.16

sworth

0.15

 description

0.15

adin

0.15

Mus

0.15

_Ptr

0.14

Ð°Ð½Ð¸ÑĨ

0.14

isse

0.14

Ned

0.14

Activations Density 0.054%

structured data fields related to program descriptions

No Comments

No Known Activations