INDEX

Explanations

references to presidential approval ratings and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

hora

-0.15

ieu

-0.15

 piger

-0.15

VIP

-0.14

horia

-0.14

adir

-0.14

holes

-0.14

 Hlav

-0.14

asse

-0.14

iolet

-0.14

POSITIVE LOGITS

 list

0.15

ç»Łè®¡

0.14

 Î´ÎµÎ´Î¿

0.14

_Query

0.14

 ÙĨØµ

0.14

loit

0.14

exceptions

0.14

 bush

0.14

 Countdown

0.14

ĺ

0.14

Activations Density 0.059%

references to presidential approval ratings and comparisons

No Comments

No Known Activations