INDEX

Explanations

elements related to scientific or technical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

áº»

-0.16

ua

-0.16

æµ©

-0.15

ubl

-0.15

Authorized

-0.14

ãĤ¢ãĥ³

-0.14

èª²

-0.14

Î±Î½Î´

-0.14

uch

-0.14

lane

-0.14

POSITIVE LOGITS

Tun

0.18

tun

0.16

ÑĨÐµÐ·

0.15

 Carn

0.15

oden

0.15

ORA

0.15

 Arthur

0.14

 orange

0.14

uzzi

0.14

 capped

0.14

Activations Density 0.019%

elements related to scientific or technical documentation

No Comments

No Known Activations