INDEX

Explanations

terms related to gaming mechanics and strategies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Ð·ÑĮ

-0.15

stad

-0.14

umba

-0.14

lio

-0.14

ISCO

-0.14

IntegerField

-0.14

ÑĥÑĢÐ½

-0.13

.ejb

-0.13

leness

-0.13

vak

-0.13

POSITIVE LOGITS

ifferent

0.14

ãĥ³ãĤ°ãĥ«

0.14

heat

0.14

abit

0.13

forme

0.13

unittest

0.13

hsi

0.13

Ã¨

0.12

unfold

0.12

awl

0.12

Activations Density 1.577%

terms related to gaming mechanics and strategies

No Comments

No Known Activations