INDEX

Explanations

references to entertainment, particularly shows and movies

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

ŀ

-0.20

ãĤ¶ãĥ¼

-0.18

elves

-0.15

ÙĨÙĬÙĨ

-0.15

 NotSupportedException

-0.15

.RichTextBox

-0.14

å¸Ń

-0.14

:UIAlert

-0.14

 Cheers

-0.14

loven

-0.13

POSITIVE LOGITS

you

0.18

adan

0.16

eru

0.15

ijken

0.15

 nobody

0.15

annel

0.15

ä½ł

0.15

 everyone

0.15

 Sure

0.14

 canh

0.14

Activations Density 0.040%

references to entertainment, particularly shows and movies

No Comments

No Known Activations