INDEX

Explanations

nouns and references to quantifiable significance or measurement, particularly in contexts related to health, science, and societal behaviors

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

emme

-0.16

Stick

-0.15

ãĥ¼ãĤ¸

-0.15

-0.14

ystick

-0.14

áºŃp

-0.14

ifo

-0.14

 Contacts

-0.14

POSITIVE LOGITS

recated

0.17

ï»¿#

0.17

MAND

0.16

Benchmark

0.15

oldt

0.14

esiz

0.14

eof

0.14

urent

0.14

emain

0.14

 OUTER

0.14

Activations Density 0.016%

nouns and references to quantifiable significance or measurement, particularly in contexts related to health, science, and societal behaviors

No Comments

No Known Activations