INDEX

Explanations

mentions of hype and anticipation related to products or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

limitations

-0.15

 limitations

-0.15

 ÐºÑĢÐ°Ð¹

-0.15

 McDon

-0.14

ingers

-0.14

insula

-0.14

à¤

-0.14

obus

-0.14

 limitation

-0.14

MUX

-0.14

POSITIVE LOGITS

Ã©p

0.15

åĩĿ

0.15

Hos

0.15

untu

0.14

ALI

0.14

gebung

0.14

ILER

0.14

.water

0.14

feld

0.14

 arrival

0.14

Activations Density 0.154%

mentions of hype and anticipation related to products or events

No Comments

No Known Activations