INDEX

Explanations

attributes and properties related to layout and dimensions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

éĢļãĤĬ

-0.14

Ð¸ÑĩÐ½Ð¾

-0.14

 Rise

-0.13

vl

-0.13

æķ·

-0.13

ìĬ

-0.13

 ÑģÐºÐ»Ð°Ð´

-0.13

issen

-0.13

POSITIVE LOGITS

PTY

0.20

.FontStyle

0.17

inks

0.16

 oppos

0.15

IPA

0.15

ledge

0.14

NCY

0.13

akis

0.13

pty

0.13

Activations Density 0.003%

attributes and properties related to layout and dimensions in code

No Comments

No Known Activations