INDEX

Explanations

mentions of various types of agencies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ØªØ±ÛĮ

-0.19

ToArray

-0.15

 supplement

-0.15

isque

-0.15

rub

-0.15

aversable

-0.14

auc

-0.14

åĿĩ

-0.14

rost

-0.14

swick

-0.14

POSITIVE LOGITS

0.18

adoo

0.16

amsung

0.16

wel

0.16

 QHBoxLayout

0.15

evice

0.15

ÏĨÎ¿

0.15

Ð¸Ð¹

0.14

eways

0.14

Activations Density 0.014%

mentions of various types of agencies

No Comments

No Known Activations